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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126232
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    technical descriptions and definitions related to coding and software libraries.

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

    This neuron detects the phrase “under the” as used in software license boilerplate.

    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
    Pretty
    -0.07
    _vec
    -0.07
    \Query
    -0.06
    traits
    -0.06
    otec
    -0.06
    precation
    -0.06
    ัพย
    -0.06
     inflict
    -0.06
     пти
    -0.06
    ikt
    -0.06
    POSITIVE LOGITS
    ').'
    0.06
    byte
    0.06
    esthetic
    0.06
    яем
    0.06
    _interfaces
    0.06
     dalla
    0.06
     Cities
    0.06
    emodel
    0.06
     chronic
    0.06
    active
    0.06
    Activations Density 0.001%

    No Known Activations