© 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. 40516
    Prev
    Next
    INDEX
    Explanations

    time references expressed in "am" or "pm"

    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
    umin
    -0.08
    inen
    -0.08
    um
    -0.07
    efe
    -0.07
    an
    -0.07
    акон
    -0.06
    sip
    -0.06
    паÑĤ
    -0.06
     Noon
    -0.06
    onomy
    -0.06
    POSITIVE LOGITS
    /pm
    0.08
    .nih
    0.07
    rowse
    0.07
    azing
    0.07
    eters
    0.06
    ην
    0.06
    linger
    0.06
    633
    0.06
    idot
    0.06
     cst
    0.06
    Activations Density 0.023%

    No Known Activations