© 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. 44279
    Prev
    Next
    INDEX
    Explanations

    Animals

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of animal experiment subjects and models (e.g., “rat,” “mouse,” “animal model,” “mice”).

    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
    strpos
    -0.07
    never
    -0.06
     issues
    -0.06
    rypton
    -0.06
    mony
    -0.06
     شب
    -0.06
    emand
    -0.06
     فوت
    -0.06
     стратег
    -0.06
    男性
    -0.06
    POSITIVE LOGITS
    写
    0.07
     rollback
    0.07
    rollback
    0.07
    .variable
    0.07
     irrigation
    0.06
     полож
    0.06
    _TEMPLATE
    0.06
     classifications
    0.06
     boot
    0.06
     pob
    0.06
    Activations Density 0.025%

    No Known Activations