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. 127033
    Prev
    Next
    INDEX
    Explanations

    regular, standard

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens related to the idea of “normal” or “regular.”

    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
     Further
    -0.07
     Giant
    -0.07
     растений
    -0.07
    ालत
    -0.07
    ']
    -0.06
     PIT
    -0.06
    Ultimately
    -0.06
     announces
    -0.06
     governor
    -0.06
     giant
    -0.06
    POSITIVE LOGITS
     traditional
    0.09
     standard
    0.09
     regular
    0.08
     normal
    0.08
     Normal
    0.07
    Standard
    0.07
     ordinary
    0.07
     Traditional
    0.07
    ΑΠ
    0.07
    .standard
    0.07
    Activations Density 0.071%

    No Known Activations