© 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. 78891
    Prev
    Next
    INDEX
    Explanations

    expressions of potential future actions or decisions

    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
    rowsable
    -0.08
    Aws
    -0.07
    uchos
    -0.07
    ="{!!
    -0.07
    ACHI
    -0.07
    úsqueda
    -0.07
     IDX
    -0.07
    niž
    -0.07
    swick
    -0.07
    ailles
    -0.06
    POSITIVE LOGITS
     scenario
    0.07
     option
    0.07
     Scenario
    0.07
     slot
    0.07
    Scenario
    0.07
     symb
    0.06
     scenarios
    0.06
    .normalized
    0.06
    ch
    0.06
     Shib
    0.06
    Activations Density 0.021%

    No Known Activations