© 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. 9-LLAMASCOPE-RES-131K
    11. 97999
    Prev
    Next
    INDEX
    Explanations

    patterns related to URL syntax and API responses

    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
    esi
    -0.07
    ecz
    -0.07
    ace
    -0.06
    eless
    -0.06
    lify
    -0.06
    wner
    -0.06
    еÑģи
    -0.06
    ilege
    -0.06
    atica
    -0.06
    ält
    -0.06
    POSITIVE LOGITS
    elsey
    0.07
    hay
    0.07
    ábado
    0.07
    Ïĥκ
    0.07
    Tween
    0.06
    tparam
    0.06
     عÙĪ
    0.06
    ç´¹
    0.06
     Äijức
    0.06
    _RATIO
    0.06
    Activations Density 0.016%

    No Known Activations