© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68788
    Prev
    Next
    INDEX
    Explanations

    thought

    np_max-act · gemini-2.0-flash

    This neuron detects words expressing personal fear or dread (e.g., “thought,” “filled,” “dread”).

    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
    123
    -0.07
     turbulence
    -0.07
    _GUI
    -0.06
    EINVAL
    -0.06
    |min
    -0.06
    _fun
    -0.06
     Wars
    -0.06
     засоб
    -0.06
    (INPUT
    -0.06
    .quiz
    -0.06
    POSITIVE LOGITS
    consider
    0.08
    ovali
    0.07
    ेवल
    0.07
     grams
    0.07
     tüm
    0.06
    igte
    0.06
     několika
    0.06
    مان
    0.06
    ož
    0.06
    UGH
    0.06
    Activations Density 0.014%

    No Known Activations