© 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. 11-RESID-POST-AA
    11. 55854
    Prev
    Next
    INDEX
    Explanations

    characters

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of a work’s characters or character-driven descriptions (e.g., “characters,” “engaging characters”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     righteous
    -0.06
     Server
    -0.06
    Conn
    -0.06
     قسمت
    -0.06
    _button
    -0.06
    Debe
    -0.06
    ège
    -0.06
    _skip
    -0.06
    Btn
    -0.06
    Joint
    -0.05
    POSITIVE LOGITS
    ?"↵
    0.07
    �
    0.07
    ffee
    0.07
    covery
    0.06
    ,’”
    0.06
    rog
    0.06
    -lined
    0.06
    hw
    0.06
    �
    0.06
    _EV
    0.06
    Activations Density 0.015%

    No Known Activations