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. 90026
    Prev
    Next
    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash

    The neuron flags semantically “content-heavy” words—key topic nouns and specialized terms rather than common function words.

    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
    Teacher
    -0.07
     redhead
    -0.06
    WindowSize
    -0.06
    نتی
    -0.06
     abrir
    -0.06
    лося
    -0.06
    (toolbar
    -0.06
    مار
    -0.06
    FileManager
    -0.06
    ใช
    -0.06
    POSITIVE LOGITS
     records
    0.07
     uncommon
    0.07
     Pat
    0.07
    _way
    0.07
     enqu
    0.07
     Rob
    0.06
    _na
    0.06
     excessively
    0.06
     prison
    0.06
     DET
    0.06
    Activations Density 0.627%

    No Known Activations