© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 20053
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    abbreviations and initialisms marked by periods (formal shorthand in names or parenthetical notation).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ested
    -0.06
     Fukushima
    -0.06
    ECTOR
    -0.06
     ashamed
    -0.06
     비밀글
    -0.06
     якій
    -0.06
    950
    -0.06
     handle
    -0.06
     thật
    -0.06
    onaut
    -0.06
    POSITIVE LOGITS
     Owned
    0.07
     cứu
    0.06
     मदद
    0.06
    Attend
    0.06
    redit
    0.06
     TInt
    0.06
     Sabha
    0.06
    ’ya
    0.06
    (Client
    0.06
    osit
    0.06
    Activations Density 0.156%

    No Known Activations