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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15-RESID-POST-AA
    6. 123182
    Prev
    Next
    INDEX
    Explanations

    dough

    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
     К
    -0.07
    igital
    -0.07
     swung
    -0.06
    vester
    -0.06
    两
    -0.06
    ugal
    -0.06
    _feat
    -0.06
    eným
    -0.06
    启
    -0.06
     rovněž
    -0.06
    POSITIVE LOGITS
    .DataGridView
    0.07
     hintText
    0.06
    .JsonProperty
    0.06
    _eng
    0.06
    [data
    0.06
    اغ
    0.06
     onBackPressed
    0.06
    NESS
    0.06
    (Network
    0.06
    _sidebar
    0.06
    Activations Density 0.007%

    No Known Activations