© 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. 72436
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or absence of evidence related to various claims or hypotheses

    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
    UDO
    -0.08
    ÄĻd
    -0.07
    agos
    -0.07
    ConverterFactory
    -0.06
    ordable
    -0.06
    azı
    -0.06
     Sokol
    -0.06
    reten
    -0.06
    ispiel
    -0.06
     дÑĢÑĥга
    -0.06
    POSITIVE LOGITS
     either
    0.13
     anywhere
    0.13
     any
    0.13
     anything
    0.12
     anybody
    0.12
     anymore
    0.11
     anyone
    0.11
    anything
    0.10
    ä»»ä½ķ
    0.10
     actually
    0.10
    Activations Density 0.019%

    No Known Activations