© 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. 15-LLAMASCOPE-RES-131K
    11. 89014
    Prev
    Next
    INDEX
    Explanations

    discussion of the importance and significance of various topics

    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
    ensing
    -0.08
    erty
    -0.08
    ensor
    -0.08
    uffers
    -0.07
    enberg
    -0.07
    horia
    -0.07
    uggy
    -0.06
    -toggler
    -0.06
    velt
    -0.06
    multiline
    -0.06
    POSITIVE LOGITS
    fully
    0.08
    eres
    0.08
    icho
    0.07
    erer
    0.07
    ingly
    0.07
    ãģĦãģ¦
    0.07
    hole
    0.07
    ìĦŃ
    0.06
     omitted
    0.06
    okus
    0.06
    Activations Density 0.006%

    No Known Activations