© 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. 85420
    Prev
    Next
    INDEX
    Explanations

    place names along with notable events or actions associated with them

    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
    acf
    -0.07
    eper
    -0.07
    anos
    -0.06
    оби
    -0.06
    ADVERTISEMENT
    -0.06
    619
    -0.06
     McKay
    -0.06
    /cms
    -0.06
    clair
    -0.06
    Screenshot
    -0.06
    POSITIVE LOGITS
    _FILENO
    0.09
    anness
    0.07
    apos
    0.07
     اÙĦØ£ÙħرÙĬÙĥÙĬØ©
    0.06
     HttpMethod
    0.06
    baz
    0.06
    _ONLY
    0.06
    ish
    0.06
    untas
    0.06
    _Lean
    0.06
    Activations Density 0.101%

    No Known Activations