© 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. 41563
    Prev
    Next
    INDEX
    Explanations

    improve

    np_max-act · gemini-2.0-flash

    This neuron fires on action verbs about improving or optimizing processes (e.g. “optimize,” “improve,” “reduce”).

    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
    rado
    -0.07
    erde
    -0.07
     Tokens
    -0.06
     elles
    -0.06
    mayı
    -0.06
    ighbour
    -0.06
     вари
    -0.06
    leyici
    -0.06
    ordes
    -0.06
     metadata
    -0.06
    POSITIVE LOGITS
     increase
    0.08
     ضد
    0.07
     arttır
    0.07
     improving
    0.06
    .documentElement
    0.06
     enhances
    0.06
    yx
    0.06
    JI
    0.06
    arrow
    0.06
    _display
    0.06
    Activations Density 0.070%

    No Known Activations