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. 53826
    Prev
    Next
    INDEX
    Explanations

    short common words

    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
     イ
    -0.07
     врем
    -0.06
    cene
    -0.06
    empresa
    -0.06
    bonus
    -0.06
     جم
    -0.06
    wins
    -0.06
    _hz
    -0.06
     cuốn
    -0.06
    bet
    -0.06
    POSITIVE LOGITS
    job
    0.07
     grad
    0.07
    urrence
    0.06
    ..<
    0.06
    _flow
    0.06
     almond
    0.06
     external
    0.06
     endpoint
    0.06
     advers
    0.06
     discontent
    0.06
    Activations Density 0.000%

    No Known Activations