© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 75008
    Prev
    Next
    INDEX
    Explanations

    h

    np_max-act · gemini-2.0-flash

    markers that denote the beginning of a speaker/header section in the conversation formatting (conversation boundary/header delimiters).

    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
    323
    -0.08
    &amp
    -0.07
     فراهم
    -0.07
    -IS
    -0.07
     aun
    -0.07
     Zust
    -0.07
    便
    -0.06
    _arrow
    -0.06
    424
    -0.06
     真
    -0.06
    POSITIVE LOGITS
    ../../../
    0.07
    čka
    0.07
     �
    0.07
    _configs
    0.07
    化学
    0.06
    лоб
    0.06
     #'
    0.06
    interfaces
    0.06
    گو
    0.06
    (Role
    0.06
    Activations Density 0.242%

    No Known Activations