© 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. 128925
    Prev
    Next
    INDEX
    Explanations

    instances of live performance and its elements

    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
     collaps
    -0.07
     unto
    -0.07
    dete
    -0.07
     Fr
    -0.06
    tring
    -0.06
    ibus
    -0.06
     temporary
    -0.06
     pari
    -0.06
     Acc
    -0.06
    GIN
    -0.06
    POSITIVE LOGITS
    dl
    0.07
     otherwise
    0.07
     interview
    0.07
    alamat
    0.07
    otherwise
    0.06
    ailles
    0.06
    cko
    0.06
    igan
    0.06
    dll
    0.06
    าà¸ļ
    0.06
    Activations Density 0.039%

    No Known Activations