© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 105004
    Prev
    Next
    INDEX
    Explanations

    Rev

    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
     pumpkin
    -0.07
     Kod
    -0.06
     cosmic
    -0.06
     donors
    -0.06
     cancer
    -0.06
    -Th
    -0.06
    _gold
    -0.06
     التاريخ
    -0.06
     corners
    -0.06
    ーの
    -0.06
    POSITIVE LOGITS
    $$$$
    0.07
     FUNC
    0.07
    .evaluate
    0.07
     exped
    0.06
     pci
    0.06
    @Resource
    0.06
     instancia
    0.06
    Disposed
    0.06
     Rossi
    0.06
     vyk
    0.06
    Activations Density 0.009%

    No Known Activations