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. 21755
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
     Pier
    -0.07
    -vector
    -0.07
    pi
    -0.06
    erald
    -0.06
    V
    -0.06
    functions
    -0.06
    Roll
    -0.06
    ining
    -0.06
    NV
    -0.06
     Wrapper
    -0.06
    POSITIVE LOGITS
     DAG
    0.07
    .endswith
    0.07
    áct
    0.07
     Begins
    0.06
    ************************************************************************
    0.06
    。不
    0.06
     Yıl
    0.06
    历史
    0.06
    .tolist
    0.06
    �
    0.06
    Activations Density 0.094%

    No Known Activations