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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 29353
    Prev
    Next
    INDEX
    Explanations

    encyclopedia articles

    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
     tamanho
    -0.08
    рь
    -0.07
    ADDR
    -0.07
    _alloc
    -0.07
    包含
    -0.06
     equity
    -0.06
    -CP
    -0.06
    Browser
    -0.06
     My
    -0.06
     вз
    -0.06
    POSITIVE LOGITS
    <Link
    0.07
     Spike
    0.07
     mos
    0.06
     vagina
    0.06
    Round
    0.06
    (datetime
    0.06
     Tier
    0.06
     eventId
    0.06
     slack
    0.06
    ánd
    0.06
    Activations Density 0.180%

    No Known Activations