© 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. 55396
    Prev
    Next
    INDEX
    Explanations

    displaying, printing, measuring devices

    np_max-act · gemini-2.0-flash

    This neuron detects terms related to displaying or rendering images (e.g., “displaying,” “images,” “exibir,” “alta resolução”).

    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
     Doesn
    -0.08
     хочу
    -0.07
    écial
    -0.06
    Russia
    -0.06
    рии
    -0.06
    toJson
    -0.06
     кирп
    -0.06
     parametro
    -0.06
    ocu
    -0.06
    (Mock
    -0.06
    POSITIVE LOGITS
    thesis
    0.07
    (sign
    0.07
     प
    0.07
     �
    0.06
     Tổng
    0.06
    _baseline
    0.06
     withdraw
    0.06
     interv
    0.06
    food
    0.06
    estre
    0.06
    Activations Density 0.130%

    No Known Activations