© 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. 68991
    Prev
    Next
    INDEX
    Explanations

    currency symbols

    np_max-act · gemini-2.0-flash

    financial metrics and performance indicators in business reports.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects numerical monetary values (currency amounts) 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
    shutdown
    -0.08
    .cluster
    -0.07
    jenis
    -0.07
     pasado
    -0.06
    uben
    -0.06
     Codec
    -0.06
    oxel
    -0.06
    Isn
    -0.06
    خش
    -0.06
     plunder
    -0.06
    POSITIVE LOGITS
    -<?
    0.07
     UITextView
    0.06
     спе
    0.06
    meter
    0.06
    .lastname
    0.06
    <?=$
    0.06
    /mp
    0.06
     cây
    0.06
     الم
    0.06
     {$
    0.06
    Activations Density 0.015%

    No Known Activations