© 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. 110196
    Prev
    Next
    INDEX
    Explanations

    control

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on first‐person self-references—especially the pronoun “I” and its contractions—marking lines where the singer speaks in the first person.

    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
    699
    -0.06
    OMP
    -0.06
    -0.06
    -manager
    -0.06
     LW
    -0.06
    OLF
    -0.06
     pierced
    -0.06
    fgang
    -0.06
     Wol
    -0.06
     Ook
    -0.06
    POSITIVE LOGITS
     dư
    0.07
    qc
    0.07
    	auth
    0.06
    ailability
    0.06
     TILE
    0.06
    (enable
    0.06
     lety
    0.06
    ıda
    0.06
     WHEN
    0.06
     apl
    0.06
    Activations Density 0.052%

    No Known Activations