© 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. 81032
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting used in licenses and legal documents

    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
    ↵
    -0.07
    1
    -0.07
    &
    -0.06
    â
    -0.06
    pe
    -0.06
    2
    -0.06
    -
    -0.06
    it
    -0.06
    and
    -0.06
    imet
    -0.06
    POSITIVE LOGITS
    /stdc
    0.10
    enderror
    0.08
    (çģ«
    0.08
    خر
    0.08
    icaret
    0.07
    FindObject
    0.07
    evenodd
    0.07
     ifndef
    0.07
    mamak
    0.07
     sublic
    0.07
    Activations Density 0.012%

    No Known Activations