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. 15-RESID-POST-AA
    6. 121131
    Prev
    Next
    INDEX
    Explanations

    St

    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
    GetString
    -0.07
    cplusplus
    -0.07
     cmdline
    -0.06
    ollapsed
    -0.06
    NamedQuery
    -0.06
     thumbs
    -0.06
     cavern
    -0.06
    redential
    -0.06
     относ
    -0.06
    DAO
    -0.06
    POSITIVE LOGITS
     St
    0.14
     ST
    0.11
    _St
    0.10
     st
    0.10
    St
    0.09
    st
    0.09
    ST
    0.08
    (st
    0.08
    (ST
    0.08
    _st
    0.08
    Activations Density 0.037%

    No Known Activations