© 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 EvalsExportsAPI 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. 128683
    Prev
    Next
    INDEX
    Explanations

    various forms of assistance and services

    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
    encent
    -0.09
    úp
    -0.08
    iterated
    -0.07
    ollah
    -0.07
    .observable
    -0.07
    osy
    -0.07
    еÑģи
    -0.07
    acman
    -0.07
    /grpc
    -0.07
    ôme
    -0.07
    POSITIVE LOGITS
     purposes
    0.10
     reasons
    0.08
     sake
    0.06
     while
    0.06
     graduating
    0.06
     reason
    0.05
     adv
    0.05
    .
    0.05
     opportunity
    0.05
     before
    0.05
    Activations Density 0.042%

    No Known Activations