© 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. 42572
    Prev
    Next
    INDEX
    Explanations

    voice

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “voice” (as in “voice‐over”)—it flags mentions of voice/voice‐over segments.

    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
    AML
    -0.07
     Lunar
    -0.07
    Lint
    -0.07
    ellen
    -0.06
    89
    -0.06
     preliminary
    -0.06
    満
    -0.06
    润
    -0.06
    anden
    -0.06
     Jenna
    -0.06
    POSITIVE LOGITS
     voice
    0.17
     Voice
    0.14
    Voice
    0.13
     voices
    0.11
     Voices
    0.10
    _voice
    0.09
    voice
    0.09
    voices
    0.09
    Vo
    0.09
    声
    0.08
    Activations Density 0.014%

    No Known Activations