© 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. 54466
    Prev
    Next
    INDEX
    Explanations

    specific coding patterns and elements related to programming functions and structures

    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
     _:
    -0.06
    doi
    -0.06
    POP
    -0.06
    lue
    -0.06
    окÑĢем
    -0.06
    aka
    -0.06
    is
    -0.06
     пеÑĢев
    -0.06
     strtok
    -0.06
    era
    -0.06
    POSITIVE LOGITS
    eneg
    0.07
     ↵↵
    0.07
    LTRB
    0.06
     neh
    0.06
     whe
    0.06
    ãĥķãĤ
    0.06
    ongsTo
    0.06
    alen
    0.06
    ↵
    0.06
     instead
    0.06
    Activations Density 0.056%

    No Known Activations