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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RESID-POST-AA
    6. 72315
    Prev
    Next
    INDEX
    Explanations

    show

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '_',
    -0.08
    (p
    -0.07
     مد
    -0.07
     jud
    -0.07
     dbHelper
    -0.06
    _R
    -0.06
    ̈
    -0.06
     wise
    -0.06
    @RequestMapping
    -0.06
    >C
    -0.06
    POSITIVE LOGITS
    ,-
    0.07
    ixa
    0.06
    195
    0.06
    .Events
    0.06
     требует
    0.06
    186
    0.06
     giochi
    0.06
     trimmed
    0.06
    iker
    0.06
    196
    0.06
    Activations Density 0.000%

    No Known Activations