© 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. 73568
    Prev
    Next
    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash

    The neuron fires on version‐number tokens (e.g. the “v=2.71…,” “vs=.3.51…,” etc.), i.e. numeric version specifiers in the text.

    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
    speech
    -0.07
     России
    -0.07
    Iterator
    -0.06
     тверд
    -0.06
     cones
    -0.06
    fitness
    -0.06
    esty
    -0.06
    -buffer
    -0.06
     carn
    -0.06
     interviewing
    -0.06
    POSITIVE LOGITS
    indows
    0.08
    ép
    0.07
    ？”↵↵
    0.06
    _AT
    0.06
    .HCM
    0.06
    esen
    0.06
    棚
    0.06
    ΟΜ
    0.06
    aday
    0.06
    bsub
    0.06
    Activations Density 0.001%

    No Known Activations