© 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. 40568
    Prev
    Next
    INDEX
    Explanations

    before

    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
     had
    -0.08
     creds
    -0.07
    CLAIM
    -0.07
     @(
    -0.07
    _DIP
    -0.06
     Message
    -0.06
     exams
    -0.06
    _encode
    -0.06
     Fed
    -0.06
    _prop
    -0.06
    POSITIVE LOGITS
    іна
    0.07
    ๊
    0.07
    lify
    0.07
     retro
    0.06
    igroup
    0.06
    měr
    0.06
    _three
    0.06
     Warner
    0.06
    ์เซ
    0.06
     soudu
    0.06
    Activations Density 0.004%

    No Known Activations