© 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. 15-LLAMASCOPE-RES-131K
    11. 27487
    Prev
    Next
    INDEX
    Explanations

    terms related to award criteria and eligibility

    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
     ph
    -0.07
    eten
    -0.06
    letic
    -0.06
     Typ
    -0.06
     Explos
    -0.06
     term
    -0.05
    edback
    -0.05
    lasses
    -0.05
    labs
    -0.05
     dip
    -0.05
    POSITIVE LOGITS
    obar
    0.08
    é»İ
    0.08
    omid
    0.08
     سÙĨØ©
    0.07
    ế
    0.07
    embro
    0.07
    ä»Ĭå¹´
    0.07
    odash
    0.07
    ccione
    0.07
    cio
    0.07
    Activations Density 0.003%

    No Known Activations