© 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. 7868
    Prev
    Next
    INDEX
    Explanations

    need help

    np_max-act · gemini-2.0-flash

    The neuron activates on language offering help or assistance (e.g. “help,” “assistance,” “something,” “appropriate”).

    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
     ファ
    -0.07
     cytok
    -0.07
    .Bottom
    -0.07
     Carmen
    -0.07
    وني
    -0.07
     دانش
    -0.07
     SERVICES
    -0.07
     пример
    -0.06
     unprotected
    -0.06
    ursal
    -0.06
    POSITIVE LOGITS
     primaryKey
    0.06
    }`);↵
    0.06
     fiercely
    0.06
    htub
    0.06
     ');
↵
    0.06
     revel
    0.06
    ',↵
    0.06
    }')
    0.06
    eldom
    0.05
    rell
    0.05
    Activations Density 0.017%

    No Known Activations