© 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. 23-RESID-POST-AA
    6. 105028
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    815
    -0.07
     AD
    -0.07
    ุก
    -0.06
    ersions
    -0.06
    $tpl
    -0.06
     Rational
    -0.06
    τρέ
    -0.06
     가입
    -0.06
    Emergency
    -0.06
    引き
    -0.06
    POSITIVE LOGITS
     setState
    0.07
    (Current
    0.07
    (worker
    0.07
    (to
    0.07
    orWhere
    0.07
    .MainActivity
    0.07
     پوست
    0.07
     CString
    0.07
     properties
    0.06
                                            
    0.06
    Activations Density 0.066%

    No Known Activations