© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110357
    Prev
    Next
    INDEX
    Explanations

    GB

    np_max-act · gemini-2.0-flash

    This neuron detects numeric hardware specifications (e.g. memory, storage, screen size, etc.) in the text.

    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
     puzzled
    -0.07
     shooter
    -0.07
     minor
    -0.07
    Sequence
    -0.07
     polarity
    -0.06
    ์ค
    -0.06
     Fixed
    -0.06
    字
    -0.06
    ₂
    -0.06
     declaring
    -0.06
    POSITIVE LOGITS
     GB
    0.07
    abyte
    0.07
    GB
    0.07
     KB
    0.06
    pliance
    0.06
    观看
    0.06
    gb
    0.06
     enormously
    0.06
    FILES
    0.06
     Trab
    0.06
    Activations Density 0.003%

    No Known Activations