© 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. 126230
    Prev
    Next
    INDEX
    Explanations

    system logs

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens—especially log timestamps, IDs, and other numbers in system‐message lines.

    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
     buf
    -0.07
     button
    -0.06
    _Title
    -0.06
    Particle
    -0.06
    rep
    -0.06
    zech
    -0.06
    ERAL
    -0.06
     Trek
    -0.06
    -eye
    -0.06
    RE
    -0.06
    POSITIVE LOGITS
    pio
    0.07
    eature
    0.07
     thưởng
    0.06
     важно
    0.06
     stran
    0.06
     SCN
    0.06
     акт
    0.06
     slug
    0.06
     bilm
    0.06
    .pageSize
    0.06
    Activations Density 0.014%

    No Known Activations