© 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. 17-LLAMASCOPE-RES-131K
    11. 3545
    Prev
    Next
    INDEX
    Explanations

    terms related to "best" and "worst."

    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
    atatype
    -0.08
    xin
    -0.08
    hed
    -0.07
     Zuk
    -0.07
    ayd
    -0.07
    itech
    -0.07
    lest
    -0.07
    vore
    -0.07
    rats
    -0.07
     numel
    -0.07
    POSITIVE LOGITS
    owing
    0.08
    ow
    0.08
    rem
    0.08
    onica
    0.07
    seller
    0.07
    owed
    0.07
    -of
    0.07
    selling
    0.07
     wishes
    0.07
    minster
    0.07
    Activations Density 0.024%

    No Known Activations