© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 31226
    Prev
    Next
    INDEX
    Explanations

    as, during

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -def
    -0.08
    ��
    -0.07
    lications
    -0.07
    iParam
    -0.07
    imbledon
    -0.07
    ขณะ
    -0.06
    مبر
    -0.06
    _REQ
    -0.06
    conv
    -0.06
    /ws
    -0.06
    POSITIVE LOGITS
    ：↵↵
    0.06
    .cookies
    0.06
     CELL
    0.06
     Cialis
    0.06
     roky
    0.05
    noopener
    0.05
    Alignment
    0.05
     만
    0.05
     JUL
    0.05
    니
    0.05
    Activations Density 0.048%

    No Known Activations