© 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. 6786
    Prev
    Next
    INDEX
    Explanations

    Music

    np_max-act · gemini-2.0-flash

    This neuron detects the word “music” (and its close morphological variants like musical, musician, etc.).

    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
    369
    -0.07
    169
    -0.06
    069
    -0.06
    _RET
    -0.06
    lep
    -0.06
    odule
    -0.06
     Repo
    -0.06
    -domain
    -0.06
    Resp
    -0.06
    Elem
    -0.06
    POSITIVE LOGITS
     music
    0.17
     Music
    0.16
    Music
    0.14
    music
    0.12
     MUSIC
    0.12
     Musical
    0.11
     musical
    0.10
     musica
    0.09
     musicians
    0.09
    .music
    0.09
    Activations Density 0.023%

    No Known Activations