© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68858
    Prev
    Next
    INDEX
    Explanations

    dialogues

    np_max-act · gemini-2.0-flash

    The neuron activates on the narrative “stage‐direction” or action‐description tokens (especially those in asterisks), i.e. when the text is giving a character’s physical actions rather than dialogue.

    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
    toContain
    -0.07
    ищ
    -0.06
    umping
    -0.06
    От
    -0.06
     اوت
    -0.06
    REE
    -0.06
     yalnızca
    -0.06
     ir
    -0.06
     flesh
    -0.06
     applicant
    -0.06
    POSITIVE LOGITS
     Estado
    0.07
    COMMENT
    0.07
    /detail
    0.07
     náv
    0.07
     �
    0.06
     productions
    0.06
     北
    0.06
    .cs
    0.06
    .exe
    0.06
     Marble
    0.06
    Activations Density 0.018%

    No Known Activations