© 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. 17-LLAMASCOPE-RES-131K
    11. 118935
    Prev
    Next
    INDEX
    Explanations

    references to specific titles and character names in literature and film

    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
    ippet
    -0.08
    ilyn
    -0.07
    haps
    -0.07
    vasive
    -0.07
    uely
    -0.07
    oje
    -0.07
    ALLY
    -0.07
    ().'/
    -0.06
    itia
    -0.06
    uria
    -0.06
    POSITIVE LOGITS
    akening
    0.06
    audi
    0.06
     Next
    0.06
     Katz
    0.06
     Wade
    0.06
    duÄŁ
    0.06
    "><!--
    0.05
     Mr
    0.05
    /The
    0.05
    nThe
    0.05
    Activations Density 0.056%

    No Known Activations