© 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. 83095
    Prev
    Next
    INDEX
    Explanations

    key concepts and questions related to theories and assumptions

    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
    linger
    -0.08
    entai
    -0.07
    .AF
    -0.07
     hete
    -0.07
    eÅŁ
    -0.07
     Ãĸr
    -0.07
    Browsable
    -0.06
    νομ
    -0.06
    stem
    -0.06
     nues
    -0.06
    POSITIVE LOGITS
     ie
    0.08
     yani
    0.08
     of
    0.07
     about
    0.07
    :
    0.07
    eed
    0.07
     involving
    0.07
    ëĮĢë¡ľ
    0.06
    odal
    0.06
     viz
    0.06
    Activations Density 0.056%

    No Known Activations