© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109255
    Prev
    Next
    INDEX
    Explanations

    Assistance and support

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric expressions and statistics (e.g. counts, percentages, decimals).

    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
     looks
    -0.06
     troops
    -0.06
    xi
    -0.06
    .sam
    -0.06
     dua
    -0.06
    vation
    -0.06
    van
    -0.06
    vd
    -0.06
     жен
    -0.06
     swarm
    -0.06
    POSITIVE LOGITS
    Sparse
    0.06
    荐
    0.06
     Casinos
    0.06
    .requires
    0.06
    .getPassword
    0.06
    :UIControlEventTouchUpInside
    0.06
     pageable
    0.06
    /remove
    0.06
    (filters
    0.06
     Laravel
    0.06
    Activations Density 0.061%

    No Known Activations