© 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. 126048
    Prev
    Next
    INDEX
    Explanations

    model network

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of machine-learning “model” terminology (e.g., “pre-trained,” “transformer,” or “model”).

    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
     by
    -0.06
    альное
    -0.06
    कर
    -0.06
    umeric
    -0.06
     Cannes
    -0.06
     Kling
    -0.06
    ää
    -0.06
     sometime
    -0.06
    346
    -0.06
    	full
    -0.06
    POSITIVE LOGITS
     جستارهای
    0.07
     облі
    0.07
    .onerror
    0.07
    深圳
    0.07
    '){
    ↵
    0.06
    \models
    0.06
     повинна
    0.06
    HasColumnName
    0.06
     сами
    0.06
     Ελλην
    0.06
    Activations Density 0.027%

    No Known Activations