© 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. 90832
    Prev
    Next
    INDEX
    Explanations

    Conversational/dialogue

    np_max-act · gemini-2.0-flash

    This neuron detects speaker‐turn labels (e.g. “Agent:”, “Customer:”, “Patient:”).

    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
    \Image
    -0.07
     кого
    -0.07
    teste
    -0.07
    .enemy
    -0.06
    race
    -0.06
     hh
    -0.06
    imal
    -0.06
    гів
    -0.06
    .Man
    -0.06
     ışık
    -0.06
    POSITIVE LOGITS
     eyed
    0.07
     محافظ
    0.07
     gaz
    0.06
     vern
    0.06
    exclusive
    0.06
     dirig
    0.06
     доказ
    0.06
     torrents
    0.06
     giveaways
    0.06
    ダイ
    0.05
    Activations Density 0.008%

    No Known Activations