© 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. 69575
    Prev
    Next
    INDEX
    Explanations

    terms related to document structure and page references

    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
    ulin
    -0.09
    asser
    -0.07
    éĶĭ
    -0.07
    emes
    -0.07
    reso
    -0.07
    ovic
    -0.07
    _cmos
    -0.06
    ÏĨι
    -0.06
    rlen
    -0.06
    OURCE
    -0.06
    POSITIVE LOGITS
    uin
    0.07
     properties
    0.07
     introduction
    0.06
    ing
    0.06
    ëŁŃ
    0.06
     princ
    0.06
     gode
    0.06
     Koh
    0.06
     framing
    0.06
    odash
    0.06
    Activations Density 0.000%

    No Known Activations