© 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. 107812
    Prev
    Next
    INDEX
    Explanations

    references to various service providers and products

    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
    afort
    -0.08
    ìłł
    -0.07
    onte
    -0.07
    stown
    -0.07
    olg
    -0.07
     EITHER
    -0.06
    _helper
    -0.06
    inis
    -0.06
    mÄĽ
    -0.06
    podob
    -0.06
    POSITIVE LOGITS
    fer
    0.06
    atoi
    0.06
    plusplus
    0.06
    TURE
    0.06
     incl
    0.06
    inclu
    0.06
    sources
    0.06
    رÙĪÙģ
    0.06
    CHAN
    0.06
    ws
    0.06
    Activations Density 0.007%

    No Known Activations