© 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. 126092
    Prev
    Next
    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the words “using” or “uses,” marking descriptions of methods or techniques.

    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
    ляем
    -0.07
     случаях
    -0.07
    (ent
    -0.07
    details
    -0.06
     milano
    -0.06
    �
    -0.06
     cultured
    -0.06
    	The
    -0.06
    umericUpDown
    -0.06
     образования
    -0.06
    POSITIVE LOGITS
     ducks
    0.06
    ordo
    0.06
     syncing
    0.06
    ILLISE
    0.06
     церкви
    0.06
     Carter
    0.06
    _SUPPORTED
    0.05
     DROP
    0.05
    sey
    0.05
    ул
    0.05
    Activations Density 0.063%

    No Known Activations