© 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. 92473
    Prev
    Next
    INDEX
    Explanations

    good

    np_max-act · gemini-2.0-flash

    The neuron fires on first-person offers or invitations—phrases like “I’m available to…,” “I’m up for a good time,” or “I could… for you.”

    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
     mActivity
    -0.07
     Compile
    -0.06
    .pagination
    -0.06
    issues
    -0.06
    .screen
    -0.06
     culo
    -0.06
     cluster
    -0.06
     قض
    -0.06
     Jack
    -0.06
     أول
    -0.06
    POSITIVE LOGITS
     destined
    0.07
     considered
    0.06
    е
    0.06
     темп
    0.06
    ('.',
    0.06
     조선
    0.06
     Legisl
    0.06
     ребенка
    0.06
     roads
    0.06
    Others
    0.06
    Activations Density 0.015%

    No Known Activations