© 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. 9364
    Prev
    Next
    INDEX
    Explanations

    and

    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
     relentlessly
    -0.07
     restrained
    -0.06
     adjustment
    -0.06
    .ctx
    -0.06
     dequeueReusableCell
    -0.06
    .RESET
    -0.06
     thuốc
    -0.06
     себ
    -0.05
     bec
    -0.05
     znaj
    -0.05
    POSITIVE LOGITS
    oncé
    0.07
    /St
    0.07
    *x
    0.07
     Hayward
    0.07
     dose
    0.07
    щие
    0.07
     LAND
    0.07
    878
    0.07
    اسية
    0.07
    lé
    0.07
    Activations Density 0.000%

    No Known Activations