Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84609
    Prev
    Next
    INDEX
    Explanations

    providing information

    np_max-act · gemini-2.0-flash
    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
    _MI
    -0.07
     repost
    -0.06
    _CERT
    -0.06
    Resp
    -0.06
     specific
    -0.06
    Correct
    -0.06
     METH
    -0.06
    Notice
    -0.06
     partisan
    -0.06
     lear
    -0.06
    POSITIVE LOGITS
    cliffe
    0.08
    크기
    0.07
     sortBy
    0.07
     "~/
    0.07
    值
    0.07
     coff
    0.07
     roads
    0.07
    ापस
    0.06
    ışma
    0.06
    .comboBox
    0.06
    Activations Density 0.562%

    No Known Activations