© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 126807
    Prev
    Next
    INDEX
    Explanations

    references to semi-finals in competitive events

    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
    inson
    -0.07
    illez
    -0.07
    åĵ¡
    -0.06
     hel
    -0.06
    PATCH
    -0.06
     maybe
    -0.06
     Gardner
    -0.06
     shame
    -0.06
     strtok
    -0.06
    anan
    -0.06
    POSITIVE LOGITS
    endoza
    0.07
    Skeleton
    0.07
    Æ°ng
    0.07
    LOSS
    0.06
    ¤ij
    0.06
    pear
    0.06
    pras
    0.06
    ambient
    0.06
    ãĥŃãĥ³
    0.06
    ì²
    0.06
    Activations Density 0.002%

    No Known Activations