Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 85
    Prev
    Next
    INDEX
    Explanations

    behavior

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on occurrences of the noun “behavior” (and its immediate context) in technical explanations.

    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
    \Log
    -0.07
    +#
    -0.07
     }),↵↵
    -0.06
     **)&
    -0.06
     پن
    -0.06
     clipboard
    -0.06
    PlainText
    -0.06
    ayas
    -0.06
    εφ
    -0.06
     Add
    -0.06
    POSITIVE LOGITS
    recht
    0.07
     radios
    0.07
     Business
    0.07
    ンティ
    0.07
    ActionButton
    0.06
     ritual
    0.06
     goodies
    0.06
    (scroll
    0.06
     quam
    0.06
     standing
    0.06
    Activations Density 0.014%

    No Known Activations