© 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. 54503
    Prev
    Next
    INDEX
    Explanations

    instances of method overrides in code

    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
    erson
    -0.07
     Dich
    -0.06
     Ard
    -0.06
     Bush
    -0.06
     Southern
    -0.06
    emon
    -0.06
    ere
    -0.05
     southern
    -0.05
    ней
    -0.05
    à¸Ĺาà¸ĩ
    -0.05
    POSITIVE LOGITS
    erras
    0.08
    HeaderCode
    0.08
     void
    0.07
    곤
    0.07
     Pai
    0.07
    ipp
    0.07
    APT
    0.07
    348
    0.07
    _INLINE
    0.07
    945
    0.07
    Activations Density 0.002%

    No Known Activations