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. 103787
    Prev
    Next
    INDEX
    Explanations

    vegetation

    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
     zem
    -0.07
    ريب
    -0.06
     Building
    -0.06
     freeing
    -0.06
     ارتفاع
    -0.06
     stirring
    -0.06
    .one
    -0.06
     jazy
    -0.06
    (queue
    -0.06
     яб
    -0.06
    POSITIVE LOGITS
    :d
    0.07
    olly
    0.07
     verwendet
    0.07
    Mike
    0.06
    (mm
    0.06
    -shell
    0.06
    _starts
    0.06
    iving
    0.06
    料無料
    0.06
    wil
    0.06
    Activations Density 0.026%

    No Known Activations