© 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. 119331
    Prev
    Next
    INDEX
    Explanations

    mentions of testing environments or controlled settings

    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
    pong
    -0.07
    erna
    -0.07
    minster
    -0.07
    OOT
    -0.06
    ạc
    -0.06
    oot
    -0.06
     fich
    -0.06
    طاÙĤ
    -0.06
     accom
    -0.06
    903
    -0.06
    POSITIVE LOGITS
    ayar
    0.07
    celik
    0.07
    itories
    0.07
    sandbox
    0.06
    aha
    0.06
    itorio
    0.06
    attery
    0.06
    ndl
    0.06
     dg
    0.06
    enler
    0.06
    Activations Density 0.000%

    No Known Activations