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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-RESID-POST-AA
    6. 9527
    Prev
    Next
    INDEX
    Explanations

    ,

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    held
    -0.06
    ."','".$
    -0.06
    itre
    -0.06
     anda
    -0.06
     UIFont
    -0.06
    DX
    -0.06
    ()='
    -0.06
    δ
    -0.06
    (CType
    -0.06
          
    -0.06
    POSITIVE LOGITS
     others
    0.07
    _iterations
    0.07
    emme
    0.07
    .instant
    0.07
    rita
    0.07
     Wolver
    0.06
    asmine
    0.06
     intestinal
    0.06
     Reasons
    0.06
    énom
    0.06
    Activations Density 0.005%

    No Known Activations