© 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. 128809
    Prev
    Next
    INDEX
    Explanations

    sound

    np_max-act · gemini-2.0-flash

    positive feedback and appreciation towards video content.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron primarily detects mentions of audio and sound—terms like “sound,” “music,” “mic(rophone),” and related audio-production words.

    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
     кас
    -0.07
     Juan
    -0.07
    _Camera
    -0.07
     шп
    -0.06
    法国
    -0.06
     англ
    -0.06
     лица
    -0.06
     Laser
    -0.06
    훈
    -0.06
    考试
    -0.06
    POSITIVE LOGITS
    Cookie
    0.06
     releases
    0.06
    IconModule
    0.06
     gid
    0.06
     thơm
    0.06
     artwork
    0.06
     roaring
    0.06
      ↵
    0.06
     category
    0.06
    Vertical
    0.05
    Activations Density 0.020%

    No Known Activations