© 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. 68965
    Prev
    Next
    INDEX
    Explanations

    ab

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of Google Colab (e.g. the “colab” token).

    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
    znik
    -0.07
     psycho
    -0.06
     pelvic
    -0.06
     Clip
    -0.06
    Instr
    -0.06
    _snapshot
    -0.06
     compounds
    -0.06
    Shape
    -0.06
     resting
    -0.06
     balances
    -0.06
    POSITIVE LOGITS
    古屋
    0.07
     ніч
    0.06
    .SuppressLint
    0.06
    .consumer
    0.06
    _MARGIN
    0.06
    �
    0.06
     Tổng
    0.06
     kolej
    0.06
     taxp
    0.06
    الإنجليزية
    0.06
    Activations Density 0.003%

    No Known Activations