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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7-RESID-POST-AA
    6. 91208
    Prev
    Next
    INDEX
    Explanations

    vasculitis

    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
     Μαρ
    -0.07
     ridge
    -0.07
     parliamentary
    -0.07
     onlara
    -0.06
    regnum
    -0.06
    พวก
    -0.06
     Bur
    -0.06
     provincia
    -0.06
    言って
    -0.06
    (Route
    -0.06
    POSITIVE LOGITS
     revised
    0.07
     Tri
    0.07
    ;t
    0.06
     redesign
    0.06
     dimensional
    0.06
    чих
    0.06
    .handleSubmit
    0.06
    enez
    0.06
    /cl
    0.06
    der
    0.06
    Activations Density 0.003%

    No Known Activations