© 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. 129720
    Prev
    Next
    INDEX
    Explanations

    Still current, not outdated

    np_max-act · gemini-2.0-flash

    The neuron fires on Cyrillic (Russian) text segments, i.e. it detects Russian‐language character sequences.

    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
    quee
    -0.06
     Luther
    -0.06
    566
    -0.06
     investor
    -0.06
    瑞
    -0.06
    686
    -0.06
    Look
    -0.06
    ียน
    -0.06
    ----------------------------------------------------------------------↵
    -0.06
    690
    -0.06
    POSITIVE LOGITS
    initely
    0.07
    .metric
    0.07
    (Guid
    0.06
     chassis
    0.06
     Music
    0.06
    (__
    0.06
     změn
    0.06
    ")));
    0.06
     av
    0.06
    -document
    0.06
    Activations Density 0.031%

    No Known Activations