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. 84772
    Prev
    Next
    INDEX
    Explanations

    light reflection/fluorescence

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of highly visible or light‐emitting materials—e.g. neon/brilliant colors, reflective or retro‐reflective surfaces, and glow-in-the-dark/luminescent effects.

    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
    قرار
    -0.07
    cancel
    -0.07
    Planning
    -0.07
     Nachricht
    -0.07
    .layout
    -0.06
     Parcelable
    -0.06
     jetzt
    -0.06
    _closed
    -0.06
     schwar
    -0.06
     kancel
    -0.06
    POSITIVE LOGITS
     auditor
    0.07
    _lr
    0.06
     regards
    0.06
    Ng
    0.06
    иг
    0.06
     passed
    0.06
    ств
    0.06
     Dolphin
    0.06
    -human
    0.06
    rix
    0.06
    Activations Density 0.007%

    No Known Activations