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. 15-RESID-POST-AA
    6. 5666
    Prev
    Next
    INDEX
    Explanations

    preparations and procedures

    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
    _DOUBLE
    -0.07
     consultant
    -0.06
     consultants
    -0.06
    ्रब
    -0.06
     hiatus
    -0.06
     손을
    -0.06
     Sterling
    -0.06
    щина
    -0.06
    remen
    -0.06
    lig
    -0.06
    POSITIVE LOGITS
    YSQL
    0.07
    _InternalArray
    0.07
    Networking
    0.07
    spNet
    0.06
    participants
    0.06
    Req
    0.06
    (tokens
    0.06
    صد
    0.06
     υ
    0.06
     TORT
    0.06
    Activations Density 0.206%

    No Known Activations