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. 19-RESID-POST-AA
    6. 110601
    Prev
    Next
    INDEX
    Explanations

    .

    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
    Less
    -0.06
    uD
    -0.06
     glGet
    -0.06
    AMI
    -0.06
     USS
    -0.06
    modules
    -0.06
    pirit
    -0.06
     Warrior
    -0.06
    _buy
    -0.06
     вмі
    -0.06
    POSITIVE LOGITS
    .:.:.:.:
    0.07
     getParent
    0.07
    ://
    0.07
    áj
    0.06
     ATM
    0.06
     ZX
    0.06
    顔
    0.06
    !");↵
    0.06
    @Json
    0.06
    Juan
    0.06
    Activations Density 0.000%

    No Known Activations