© 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 EvalsExportsinterp-engineNEWAPI 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. 91917
    Prev
    Next
    INDEX
    Explanations

    references to possession and handling of the ball in sports contexts

    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
    etto
    -0.07
    ly
    -0.06
     part
    -0.06
    ired
    -0.06
    fully
    -0.06
    ously
    -0.06
    807
    -0.06
     vast
    -0.06
     grade
    -0.06
    ir
    -0.06
    POSITIVE LOGITS
     Scalars
    0.08
    aset
    0.08
    ImageContext
    0.07
    ignet
    0.07
     HOLDER
    0.07
    eyse
    0.07
    HeaderCode
    0.07
    RuleContext
    0.07
    centre
    0.07
    inspace
    0.07
    Activations Density 0.009%

    No Known Activations