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. 92676
    Prev
    Next
    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash

    The neuron specifically detects floating‐point numeric tokens (decimal numbers) such as the precise census percentages and area fractions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    data related to population statistics of towns and cities.

    oai_token-act-pair · gpt-4o-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
    			
    -0.07
    ';";↵
    -0.06
     tubing
    -0.06
    Amazing
    -0.06
    Printing
    -0.06
     ignition
    -0.06
    .RelativeLayout
    -0.06
     보고
    -0.06
    Console
    -0.06
     object
    -0.06
    POSITIVE LOGITS
    (END
    0.07
    -inc
    0.07
    +",
    0.07
    套
    0.06
     WAY
    0.06
     firstname
    0.06
    recht
    0.06
    !“
    0.06
     вред
    0.06
    LIN
    0.06
    Activations Density 0.001%

    No Known Activations