© 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. 92514
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    information about population statistics in geographic locations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron flags numeric tokens containing decimal points (i.e. fractional or percentage 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
    script
    -0.07
    lying
    -0.06
    ula
    -0.06
     Walnut
    -0.06
    fv
    -0.06
     corpses
    -0.06
     TMP
    -0.05
    lined
    -0.05
     Thanks
    -0.05
    Routine
    -0.05
    POSITIVE LOGITS
    (".",
    0.07
    .Tensor
    0.07
    ्रश
    0.07
    产业
    0.07
    Georgia
    0.06
     sog
    0.06
    _hw
    0.06
    ATEGY
    0.06
    (":
    0.06
    _production
    0.06
    Activations Density 0.000%

    No Known Activations