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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23-RESID-POST-AA
    6. 103946
    Prev
    Next
    INDEX
    Explanations

    plot descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    のか
    -0.07
     L
    -0.07
    .When
    -0.06
     música
    -0.06
    Span
    -0.06
    สาย
    -0.06
    leh
    -0.06
    장이
    -0.06
    овах
    -0.06
     adapter
    -0.06
    POSITIVE LOGITS
    阅读
    0.07
    $/
    0.06
    _crypto
    0.06
     ancestral
    0.06
    рест
    0.06
    iphery
    0.06
    RowIndex
    0.06
    -transfer
    0.06
    нат
    0.06
    (itemView
    0.06
    Activations Density 0.019%

    No Known Activations