© 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. 125170
    Prev
    Next
    INDEX
    Explanations

    defense

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of legal advocates and courtroom counsel (e.g. “defense counsel,” “prosecution,” attorney references).

    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
     poil
    -0.07
    _MIDDLE
    -0.06
     printing
    -0.06
    ;}↵
    -0.06
     freeze
    -0.06
     creampie
    -0.06
    pass
    -0.06
    створ
    -0.06
     mağ
    -0.06
    (ent
    -0.06
    POSITIVE LOGITS
     Transformer
    0.07
    :pk
    0.07
     chassis
    0.07
    _lastname
    0.07
     čas
    0.07
     دين
    0.06
    Trait
    0.06
    列表
    0.06
     �
    0.06
    //================================================================
    0.06
    Activations Density 0.009%

    No Known Activations