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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125133
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating frequency or typicality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ief
    -0.07
    arte
    -0.07
    awy
    -0.07
    и
    -0.07
    gs
    -0.06
    oi
    -0.06
    iam
    -0.06
     Saw
    -0.06
    ge
    -0.06
    ail
    -0.06
    POSITIVE LOGITS
     speaking
    0.07
    spe
    0.07
     there
    0.07
     же
    0.07
    avin
    0.06
    ä¹İ
    0.06
     ли
    0.06
    ,
    0.06
    617
    0.06
    these
    0.06
    Activations Density 0.048%

    No Known Activations