© 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. 85356
    Prev
    Next
    INDEX
    Explanations

    temporal references related to transfer activities in sports

    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
    nit
    -0.06
    916
    -0.06
    icz
    -0.06
    xaa
    -0.06
    AIL
    -0.06
     Fior
    -0.06
     Lawyers
    -0.06
    elsius
    -0.06
    -medium
    -0.06
    icult
    -0.06
    POSITIVE LOGITS
    ements
    0.07
     Redistributions
    0.06
    _cpus
    0.06
    atory
    0.06
    rove
    0.06
    Unsigned
    0.06
    .sig
    0.06
     Ä°l
    0.06
    edReader
    0.06
    osg
    0.06
    Activations Density 0.017%

    No Known Activations