© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129678
    Prev
    Next
    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash

    The neuron primarily fires on Go function declarations (i.e. the “func …” lines).

    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
     tc
    -0.07
     touches
    -0.06
     antes
    -0.06
    _RATE
    -0.06
    -produ
    -0.06
     rushing
    -0.06
     Guill
    -0.06
     backlight
    -0.06
     фото
    -0.06
    迅
    -0.06
    POSITIVE LOGITS
     freeway
    0.06
    這
    0.06
     frag
    0.06
    】↵↵
    0.06
     Chairs
    0.06
    Salary
    0.06
    oured
    0.06
     Accepted
    0.06
    monthly
    0.06
    mc
    0.06
    Activations Density 0.011%

    No Known Activations