© 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. 55871
    Prev
    Next
    INDEX
    Explanations

    references to programming practices and guidelines

    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
    erti
    -0.08
    leston
    -0.07
     Pres
    -0.06
    raw
    -0.06
    rella
    -0.06
    431
    -0.06
     beden
    -0.06
    unger
    -0.06
    nbsp
    -0.06
    æĿĥéĻIJ
    -0.06
    POSITIVE LOGITS
    Style
    0.09
     Style
    0.09
     conventions
    0.09
     adopted
    0.08
     style
    0.08
    Lint
    0.08
    _STYLE
    0.08
     STYLE
    0.07
     adoption
    0.07
    STYLE
    0.07
    Activations Density 0.014%

    No Known Activations