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

    Neuronpedia

    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. 126093
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operations

    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
    ieber
    -0.08
    reff
    -0.07
    jom
    -0.07
    기ê´Ģ
    -0.07
    ustil
    -0.07
    ndef
    -0.06
    lom
    -0.06
    Invoker
    -0.06
    encent
    -0.06
    VEC
    -0.06
    POSITIVE LOGITS
     cancel
    0.06
     div
    0.06
    DEST
    0.06
     cancellation
    0.06
     canceled
    0.06
     grave
    0.06
     cancell
    0.06
    xFFFFFF
    0.06
    ucci
    0.06
     canc
    0.06
    Activations Density 0.004%

    No Known Activations