© 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. 104264
    Prev
    Next
    INDEX
    Explanations

    references to images or visuals

    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
    oš
    -0.06
     Leo
    -0.06
    ocket
    -0.06
     already
    -0.06
    https
    -0.06
    gregator
    -0.06
     Austr
    -0.05
     steep
    -0.05
     Mehr
    -0.05
     way
    -0.05
    POSITIVE LOGITS
     jadx
    0.07
    tap
    0.07
    /stdc
    0.07
    sti
    0.07
    OLON
    0.07
    TOTYPE
    0.07
    inux
    0.07
     forState
    0.06
    á»ĵng
    0.06
    åŁĭ
    0.06
    Activations Density 0.002%

    No Known Activations