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

    Neuronpedia

    APICircuit 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. 11-RESID-POST-AA
    6. 80858
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     音
    -0.07
    ';";↵
    -0.06
     เค
    -0.06
    @NoArgsConstructor
    -0.06
     เซ
    -0.06
     weer
    -0.06
    џџџ
    -0.06
    _PICK
    -0.06
    (utils
    -0.06
    415
    -0.06
    POSITIVE LOGITS
    enuous
    0.07
     proficiency
    0.07
     terrifying
    0.07
     Ranked
    0.06
     Accountability
    0.06
    Serialized
    0.06
     stemmed
    0.06
    ooth
    0.06
    index
    0.06
     notifying
    0.06
    Activations Density 0.002%

    No Known Activations