© 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. 91574
    Prev
    Next
    INDEX
    Explanations

    helpful

    np_max-act · gemini-2.0-flash

    This neuron responds strongly to the word “helpful” (as in the phrase “a helpful and … response”).

    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
    inction
    -0.07
    manifest
    -0.07
    えた
    -0.07
     critique
    -0.07
     variety
    -0.06
    δο
    -0.06
    ữa
    -0.06
    出去
    -0.06
    -expanded
    -0.06
    .ColumnHeadersHeightSizeMode
    -0.06
    POSITIVE LOGITS
    VERN
    0.06
     yards
    0.06
     Shib
    0.06
     वर
    0.06
     řid
    0.06
     ponto
    0.06
     Losing
    0.06
     Osw
    0.06
     Nissan
    0.06
     Leer
    0.06
    Activations Density 0.014%

    No Known Activations