© 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. 15-LLAMASCOPE-RES-131K
    11. 26879
    Prev
    Next
    INDEX
    Explanations

    references to numerical values and descriptions of ratios or comparisons

    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
    ouncill
    -0.07
    erald
    -0.06
    fst
    -0.06
     Wayback
    -0.06
    reamble
    -0.06
    GENCY
    -0.06
    ednou
    -0.06
    ä½ĵ
    -0.06
    ustom
    -0.06
    urse
    -0.06
    POSITIVE LOGITS
     equivalent
    0.10
     Equivalent
    0.08
     equivalents
    0.08
    #ad
    0.08
    Equivalent
    0.08
    ÑĤÑı
    0.07
    .beta
    0.07
     jadx
    0.07
    $MESS
    0.07
    makta
    0.07
    Activations Density 0.015%

    No Known Activations