© 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. 38618
    Prev
    Next
    INDEX
    Explanations

    specific dates and calendar mentions

    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
    ãĥ¢ãĥ³
    -0.08
    iaux
    -0.07
    theid
    -0.07
    ilen
    -0.07
    umuz
    -0.07
    olk
    -0.07
    Ùį
    -0.07
    oste
    -0.07
    å§ĭ
    -0.07
     Armed
    -0.06
    POSITIVE LOGITS
    lessly
    0.10
    wards
    0.09
    itionally
    0.08
    ewise
    0.08
    -wise
    0.08
    ensively
    0.08
    ologically
    0.08
    aneously
    0.08
    istically
    0.07
    grily
    0.07
    Activations Density 0.045%

    No Known Activations