© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44391
    Prev
    Next
    INDEX
    Explanations

    Kaplan

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens and associated statistical‐analysis markers (e.g. Kaplan-Meier estimates, log-rank, hazard ratios, and p-values).

    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
    .Unmarshal
    -0.06
     Piano
    -0.06
     sponge
    -0.06
    \
    ↵
    -0.06
     hires
    -0.06
    463
    -0.06
    "'↵
    -0.06
    %%*/
    -0.06
    渐
    -0.06
    ******↵
    -0.06
    POSITIVE LOGITS
    ा)
    0.07
     Canonical
    0.07
     BOT
    0.06
     sulph
    0.06
     custom
    0.06
     maximizing
    0.06
     Py
    0.06
    langs
    0.06
    keeper
    0.06
    ورة
    0.06
    Activations Density 0.001%

    No Known Activations