© 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. 84300
    Prev
    Next
    INDEX
    Explanations

    references to celebrations and significant events

    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
    ody
    -0.06
    isbury
    -0.06
    Ont
    -0.06
    ductor
    -0.06
    220
    -0.06
    pect
    -0.06
    arcy
    -0.06
    kie
    -0.06
    _ENABLED
    -0.06
    ERCHANT
    -0.06
    POSITIVE LOGITS
     bằng
    0.07
     with
    0.07
    aan
    0.07
     limburg
    0.07
     differently
    0.07
    _sparse
    0.06
    GuidId
    0.06
    ueur
    0.06
    igung
    0.06
     dengan
    0.06
    Activations Density 0.021%

    No Known Activations