© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 88179
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    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
    eras
    -0.07
     ì¤Ģ
    -0.07
     stab
    -0.07
    comb
    -0.07
     Halk
    -0.06
    á»Ļng
    -0.06
    toolbox
    -0.06
    ernal
    -0.06
    лик
    -0.06
    ustil
    -0.06
    POSITIVE LOGITS
    isin
    0.08
    utin
    0.08
    GIN
    0.07
     Hussein
    0.06
    alic
    0.06
    ór
    0.06
     Eisen
    0.06
    865
    0.06
    366
    0.06
    VisualStyle
    0.06
    Activations Density 0.129%

    No Known Activations