© 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. 92428
    Prev
    Next
    INDEX
    Explanations

    France

    np_max-act · gemini-2.0-flash

    The neuron broadly flags proper‐name tokens – especially organizational, place, or other named‐entity labels.

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

    terms related to scientific research and methodologies.

    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
     comentarios
    -0.07
     及
    -0.07
    -su
    -0.06
     caratter
    -0.06
    Mbps
    -0.06
     hòa
    -0.06
    ा,
    -0.06
    tw
    -0.06
     jazy
    -0.06
     vom
    -0.06
    POSITIVE LOGITS
    .fr
    0.09
    Jean
    0.08
     Pierre
    0.07
    ôme
    0.07
     Quebec
    0.07
    ueil
    0.07
     France
    0.07
     French
    0.07
     Jean
    0.07
    ître
    0.07
    Activations Density 0.347%

    No Known Activations