© 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. 13062
    Prev
    Next
    INDEX
    Explanations

    rejection

    np_max-act · gemini-2.0-flash

    requests for guidance on unethical or illegal activities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron never activates (all its activation values are zero), so it does not detect or respond to any patterns in the input.

    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
     voz
    -0.07
     riv
    -0.06
    BYTE
    -0.06
     conf
    -0.06
     CIT
    -0.06
     zou
    -0.06
    �
    -0.06
    isky
    -0.06
     fabs
    -0.06
    藍
    -0.06
    POSITIVE LOGITS
     glad
    0.07
    probante
    0.07
    _genre
    0.07
     avoided
    0.06
     durumlarda
    0.06
    .*;↵
    0.06
     seinem
    0.06
    .tipo
    0.06
     confirmation
    0.06
     chủ
    0.06
    Activations Density 0.002%

    No Known Activations