© 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. 15-RESID-POST-AA
    6. 68998
    Prev
    Next
    INDEX
    Explanations

    ages or time

    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_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
    equals
    -0.07
    Err
    -0.07
    ashed
    -0.07
     amplified
    -0.07
    =@
    -0.06
     z
    -0.06
    ugar
    -0.06
    -ft
    -0.06
    itated
    -0.06
    ashing
    -0.06
    POSITIVE LOGITS
    osate
    0.06
    保
    0.06
    (lua
    0.06
    łą
    0.06
     tỷ
    0.06
    $password
    0.06
     floatValue
    0.06
     الوص
    0.06
     attributable
    0.06
     Ре
    0.06
    Activations Density 0.007%

    No Known Activations