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. 15-RESID-POST-AA
    6. 12323
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kontakt
    -0.07
     XF
    -0.07
    \\\\
    -0.06
    iniz
    -0.06
     Congo
    -0.06
     Difference
    -0.06
    嫌
    -0.06
     todo
    -0.06
     entrar
    -0.06
    _gen
    -0.06
    POSITIVE LOGITS
    manifest
    0.07
    emi
    0.06
    cret
    0.06
    -facebook
    0.06
    =image
    0.06
     гар
    0.06
    veillance
    0.06
     года
    0.06
    CGFloat
    0.06
    ouncill
    0.06
    Activations Density 0.017%

    No Known Activations