© 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. 69928
    Prev
    Next
    INDEX
    Explanations

    references to sports news and reporting

    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
    Reviewer
    -0.07
     Reviews
    -0.07
    ãĥ¬ãĥĵ
    -0.07
    UserCode
    -0.07
    Reviews
    -0.07
    ectl
    -0.07
    èĶµ
    -0.07
     wiki
    -0.06
     REVIEW
    -0.06
    _SOC
    -0.06
    POSITIVE LOGITS
     statuses
    0.08
     @
    0.07
     (@
    0.07
     reporting
    0.07
     Status
    0.06
     Graves
    0.06
    /status
    0.06
     sources
    0.06
     Covers
    0.06
     colum
    0.06
    Activations Density 0.009%

    No Known Activations