© 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. 19-RESID-POST-AA
    11. 35482
    Prev
    Next
    INDEX
    Explanations

    If

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tools
    -0.06
    ’aut
    -0.06
    划
    -0.06
     carriers
    -0.06
    /licenses
    -0.06
     게시물
    -0.06
    28
    -0.06
     EditText
    -0.06
     الميلاد
    -0.06
    表
    -0.06
    POSITIVE LOGITS
    monary
    0.06
    246
    0.06
     kont
    0.06
    -treated
    0.06
    tered
    0.06
    iffer
    0.06
    099
    0.06
    @RequestMapping
    0.06
     потол
    0.06
    _RUN
    0.06
    Activations Density 0.058%

    No Known Activations