© 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. 6782
    Prev
    Next
    INDEX
    Explanations

    plus or minus

    np_max-act · gemini-2.0-flash

    This neuron is inactive (it never responds to any input).

    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
     Few
    -0.07
    	h
    -0.07
     Two
    -0.06
     vice
    -0.06
     Georges
    -0.06
     Wol
    -0.06
     tokenId
    -0.06
     fees
    -0.06
     Registers
    -0.06
    isches
    -0.06
    POSITIVE LOGITS
     amacı
    0.06
    تور
    0.06
     premiere
    0.06
    perf
    0.06
    engage
    0.06
    competition
    0.06
    (adapter
    0.06
    Canon
    0.06
     anon
    0.06
    เทคโนโลย
    0.06
    Activations Density 0.001%

    No Known Activations