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. 91376
    Prev
    Next
    INDEX
    Explanations

    grammar and sentence structure

    np_max-act · gemini-2.0-flash

    This neuron remains inactive (zero response) on all tokens and thus does not detect any specific pattern.

    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
    alis
    -0.07
    _std
    -0.07
    ayacak
    -0.07
    ITS
    -0.06
    tım
    -0.06
     environmentally
    -0.06
    šel
    -0.06
     ما
    -0.06
     diagnostic
    -0.06
    Acceler
    -0.06
    POSITIVE LOGITS
     Knicks
    0.07
    (--
    0.06
     Gameplay
    0.06
                                           
    0.06
     spills
    0.06
    ........
    0.06
    There
    0.06
    (graph
    0.06
     NI
    0.06
     ::=
    0.06
    Activations Density 0.038%

    No Known Activations