© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30105
    Prev
    Next
    INDEX
    Explanations

    pagination code

    np_max-act · gemini-2.0-flash

    The neuron detects words related to pagination controls (e.g. “page,” “pages,” “pagination,” “links,” “paginating”).

    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
    ικών
    -0.06
     seule
    -0.06
     occur
    -0.06
    /docs
    -0.06
     FIFO
    -0.06
    adam
    -0.06
    être
    -0.06
     absurd
    -0.06
     bless
    -0.06
     Sentry
    -0.06
    POSITIVE LOGITS
     nav
    0.07
     espan
    0.07
    .total
    0.07
     '..
    0.07
     fantasy
    0.06
     uint
    0.06
     accidentally
    0.06
     adultos
    0.06
     Road
    0.06
     scri
    0.06
    Activations Density 0.006%

    No Known Activations