© 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. 8782
    Prev
    Next
    INDEX
    Explanations

    good

    np_max-act · gemini-2.0-flash

    This neuron activates on positive evaluative adjectives (e.g., “great,” “good”) signaling a favorable opinion.

    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
     structs
    -0.07
     technolog
    -0.07
    _objs
    -0.06
    .command
    -0.06
    @WebServlet
    -0.06
     rather
    -0.06
     wealthy
    -0.06
    année
    -0.06
    Capabilities
    -0.06
    (entity
    -0.06
    POSITIVE LOGITS
     ads
    0.06
    _Name
    0.06
     criminal
    0.06
    chema
    0.06
    ";
    ↵
    0.06
    리즈
    0.06
    _IC
    0.06
    สว
    0.06
     secured
    0.06
     asymmetric
    0.06
    Activations Density 0.009%

    No Known Activations