© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129138
    Prev
    Next
    INDEX
    Explanations

    titles and references in academic or scholarly texts

    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
    pite
    -0.08
    moth
    -0.07
    edii
    -0.07
     createSelector
    -0.07
    èo
    -0.07
    aul
    -0.07
    sie
    -0.07
    abh
    -0.06
    sic
    -0.06
     adipiscing
    -0.06
    POSITIVE LOGITS
    webkit
    0.13
    /+
    0.07
     PowerPoint
    0.07
    urnal
    0.06
    illions
    0.06
    iyan
    0.06
    yl
    0.06
    vs
    0.06
     Ent
    0.06
    velt
    0.06
    Activations Density 0.078%

    No Known Activations