© 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. 75225
    Prev
    Next
    INDEX
    Explanations

    help

    np_max-act · gemini-2.0-flash

    This neuron appears to be effectively “dead,” never activating in response to any of the input.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    content related to harmful or abusive behaviors.

    oai_token-act-pair · gpt-4o-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
    _should
    -0.06
    adık
    -0.06
     TPP
    -0.06
     θε
    -0.06
     irritating
    -0.06
     Tubes
    -0.06
    ерти
    -0.06
    _hd
    -0.06
    _SW
    -0.06
    昇
    -0.06
    POSITIVE LOGITS
    _models
    0.07
    andise
    0.06
     ADVISED
    0.06
     outbreaks
    0.06
    amment
    0.06
    】↵↵
    0.06
    ーブ
    0.06
    >y
    0.06
    ">',↵
    0.06
     deficiency
    0.06
    Activations Density 0.043%

    No Known Activations