© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95525
    Prev
    Next
    INDEX
    Explanations

    instances of the word "on" and numerical data points indicating measurements or statistics

    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
    oven
    -0.09
    legg
    -0.08
    urrent
    -0.07
    wash
    -0.07
    elib
    -0.07
    reeze
    -0.07
    ToFit
    -0.07
    istant
    -0.07
    upiter
    -0.07
    airo
    -0.07
    POSITIVE LOGITS
    viso
    0.06
     Fro
    0.06
    engo
    0.06
    Indexed
    0.06
     Druh
    0.06
    .Dec
    0.06
    ivi
    0.06
    ICK
    0.06
    .limit
    0.06
    Wildcard
    0.05
    Activations Density 0.003%

    No Known Activations