© 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. 28774
    Prev
    Next
    INDEX
    Explanations

    special symbols or markers that signify important points or annotations within the text

    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
    ort
    -0.07
    anko
    -0.06
    nel
    -0.06
    ienne
    -0.06
    sworth
    -0.06
    r
    -0.06
    ww
    -0.06
     Superior
    -0.06
    p
    -0.06
    ity
    -0.06
    POSITIVE LOGITS
    IVED
    0.10
    VED
    0.08
    .useState
    0.07
    celik
    0.07
    .gdx
    0.07
    μά
    0.07
    cular
    0.07
    --*/↵
    0.07
    CallCheck
    0.07
    .createServer
    0.07
    Activations Density 0.007%

    No Known Activations