© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91440
    Prev
    Next
    INDEX
    Explanations

    contributor

    np_max-act · gemini-2.0-flash

    information related to software package metadata and maintenance duties.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on occurrences of “Contributor” (and its variants like “contributors” or “contributions”), i.e. labels or tokens marking contributor metadata.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _NULL
    -0.07
     phase
    -0.06
     任
    -0.06
     près
    -0.06
     barred
    -0.06
     Scheme
    -0.06
     linkage
    -0.06
     escol
    -0.06
    @@@@
    -0.06
     LDAP
    -0.06
    POSITIVE LOGITS
     contributor
    0.10
     contributors
    0.08
     writers
    0.08
     Contributor
    0.08
     Clifford
    0.07
     оскільки
    0.07
     contributed
    0.07
    	elsif
    0.07
    .servers
    0.07
    kı
    0.07
    Activations Density 0.007%

    No Known Activations