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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7586
    Prev
    Next
    INDEX
    Explanations

    technical 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
    Any
    -0.08
     từ
    -0.07
    我的
    -0.06
     butt
    -0.06
     Any
    -0.06
     gratuiti
    -0.06
     blev
    -0.06
     öğrenc
    -0.06
    charted
    -0.06
     λίγ
    -0.06
    POSITIVE LOGITS
    ρηση
    0.07
    structural
    0.07
    inputEmail
    0.07
    ->[
    0.06
    relative
    0.06
    -fr
    0.06
    /she
    0.06
     sever
    0.06
     airl
    0.06
    vrier
    0.06
    Activations Density 0.188%

    No Known Activations