Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73503
    Prev
    Next
    INDEX
    Explanations

    errors

    np_max-act · gemini-2.0-flash

    The neuron fires on log or console lines reporting errors or exceptions (e.g. text around “error occurred,” “failed,” etc.).

    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
    iversary
    -0.08
    fad
    -0.07
     bla
    -0.07
    жен
    -0.06
    หร
    -0.06
    polate
    -0.06
     semiclassical
    -0.06
    ัต
    -0.06
     перем
    -0.06
    gebra
    -0.06
    POSITIVE LOGITS
     diving
    0.07
    #",
    0.06
     '('
    0.06
    _possible
    0.06
     yerine
    0.06
    -found
    0.06
     suppose
    0.06
     Slider
    0.06
     overlapping
    0.06
    Gravity
    0.06
    Activations Density 0.003%

    No Known Activations