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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125374
    Prev
    Next
    INDEX
    Explanations

    references to future planning or development

    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
    缮åīį
    -0.07
     Matter
    -0.07
    LOUR
    -0.07
     lately
    -0.06
    Ì
    -0.06
     konci
    -0.06
    createFrom
    -0.06
     tük
    -0.06
    .constructor
    -0.06
    ixin
    -0.06
    POSITIVE LOGITS
     generations
    0.11
    -proof
    0.11
    /current
    0.10
    -generation
    0.08
    ebin
    0.08
    amarin
    0.07
    proof
    0.07
    otron
    0.07
    fully
    0.07
     iterations
    0.07
    Activations Density 0.012%

    No Known Activations