© 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. 126729
    Prev
    Next
    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash

    references to biological processes involving DNA and genetic factors.

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

    This neuron detects fragments of author names in citations (i.e. tokens from bibliographic references).

    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
    *_
    -0.07
     Az
    -0.06
    Scar
    -0.06
    emsp
    -0.06
     "_
    -0.06
     HttpHeaders
    -0.06
    Wrong
    -0.06
    Canon
    -0.06
    credentials
    -0.06
    .desc
    -0.06
    POSITIVE LOGITS
    ��
    0.06
    develop
    0.06
     Slater
    0.06
     generado
    0.06
     Jury
    0.06
    .thread
    0.06
     vibe
    0.06
    äd
    0.06
     Madness
    0.06
    뮤
    0.06
    Activations Density 0.035%

    No Known Activations