© 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. 73230
    Prev
    Next
    INDEX
    Explanations

    terms related to the management and usage of information or data

    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
    osate
    -0.07
    etz
    -0.07
    stoi
    -0.07
    wat
    -0.07
     DISCLAIM
    -0.07
     McB
    -0.06
    elementType
    -0.06
    _HC
    -0.06
    Lookup
    -0.06
    etch
    -0.06
    POSITIVE LOGITS
     tort
    0.07
     collection
    0.07
    éŀ
    0.06
    0.06
     ret
    0.06
     storage
    0.06
    andler
    0.06
     butt
    0.06
     s
    0.06
     other
    0.05
    Activations Density 0.001%

    No Known Activations