© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 27624
    Prev
    Next
    INDEX
    Explanations

    197

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    okable
    -0.07
     predicates
    -0.06
    ampp
    -0.06
    \<
    -0.06
     неиз
    -0.06
     Kop
    -0.06
    ько
    -0.06
    jom
    -0.06
    CUR
    -0.06
     blat
    -0.06
    POSITIVE LOGITS
    196
    0.09
    194
    0.08
    197
    0.08
    195
    0.07
    199
    0.07
    .instagram
    0.07
    191
    0.07
    198
    0.07
    208
    0.07
    192
    0.07
    Activations Density 0.001%

    No Known Activations