© 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. 7820
    Prev
    Next
    INDEX
    Explanations

    size and dimensions

    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
    _near
    -0.07
     EXPRESS
    -0.06
     Setting
    -0.06
     tre
    -0.06
    ！”↵↵
    -0.06
    dto
    -0.06
    __
    -0.06
    >()↵↵
    -0.06
     Day
    -0.06
    .set
    -0.06
    POSITIVE LOGITS
     جدا
    0.08
    (Dialog
    0.07
     tangled
    0.07
     výrob
    0.07
     realise
    0.07
    imbledon
    0.07
    Unmount
    0.06
    maxcdn
    0.06
    _InitStruct
    0.06
     употреб
    0.06
    Activations Density 0.023%

    No Known Activations