© 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. 126639
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to parenthetical or bracketed alternate‐title or release‐info annotations (e.g. “released as…,” “US Title: …”).

    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
    면
    -0.08
    出
    -0.07
    .detail
    -0.06
     IA
    -0.06
    (MAX
    -0.06
    qv
    -0.06
     guru
    -0.06
    Ka
    -0.06
     zad
    -0.06
    -ms
    -0.06
    POSITIVE LOGITS
     sufferers
    0.07
    .subtitle
    0.07
     протяж
    0.07
    .Storage
    0.07
     Öğren
    0.06
    erap
    0.06
     nhiễ
    0.06
    olec
    0.06
     удар
    0.06
    isiyle
    0.06
    Activations Density 0.014%

    No Known Activations