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. 23-RESID-POST-AA
    6. 104335
    Prev
    Next
    INDEX
    Explanations

    =

    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
    かった
    -0.07
     okum
    -0.07
     groin
    -0.06
    ONEY
    -0.06
    805
    -0.06
     воз
    -0.06
     olan
    -0.06
    ейн
    -0.06
     правда
    -0.06
    apes
    -0.06
    POSITIVE LOGITS
    >Data
    0.07
     cerr
    0.06
     constantly
    0.06
     статті
    0.06
    >'.
    0.06
    >'.$
    0.06
    .schedulers
    0.06
     PHPUnit
    0.06
    Lifecycle
    0.06
     sends
    0.06
    Activations Density 0.012%

    No Known Activations