© 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. 68988
    Prev
    Next
    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (especially version or schema numbers) in XML and similar markup.

    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
    .dup
    -0.08
    _Un
    -0.07
    嫌
    -0.07
    -record
    -0.07
    .roles
    -0.07
    ("|
    -0.07
    )은
    -0.07
     باعث
    -0.06
    aná
    -0.06
    iforn
    -0.06
    POSITIVE LOGITS
    3
    0.07
     paddingLeft
    0.07
    we
    0.07
     PTSD
    0.07
     zurück
    0.07
     darkness
    0.06
     dense
    0.06
    getX
    0.06
     thesis
    0.06
     Ce
    0.06
    Activations Density 0.002%

    No Known Activations