© 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. 69947
    Prev
    Next
    INDEX
    Explanations

    technical programming terms and error messages related to coding contexts

    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
    eydi
    -0.08
    รม
    -0.07
    ÅĻe
    -0.07
    θÏħ
    -0.07
    mos
    -0.06
    orch
    -0.06
    reed
    -0.06
    awan
    -0.06
    antro
    -0.06
    qed
    -0.06
    POSITIVE LOGITS
    ;if
    0.06
    еÑĢин
    0.06
    iked
    0.06
     Singles
    0.06
    obs
    0.06
    illion
    0.06
    enez
    0.06
    acks
    0.06
    ủi
    0.06
    _DIRECT
    0.06
    Activations Density 0.028%

    No Known Activations