© 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. 54244
    Prev
    Next
    INDEX
    Explanations

    HTTP status codes and API response patterns

    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
     w
    -0.07
    656
    -0.06
    313
    -0.06
    713
    -0.06
    863
    -0.06
    esson
    -0.06
    343
    -0.06
     related
    -0.06
    241
    -0.06
    373
    -0.06
    POSITIVE LOGITS
    chers
    0.08
    oice
    0.08
    trak
    0.08
    teg
    0.08
    pend
    0.07
    иÑĤом
    0.07
    tach
    0.07
    elper
    0.07
    (æĹ¥
    0.07
    chio
    0.07
    Activations Density 0.004%

    No Known Activations