© 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. 126891
    Prev
    Next
    INDEX
    Explanations

    significant numerical data or statements related to industries and events

    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
    fter
    -0.08
     GetLastError
    -0.07
    lood
    -0.06
     driving
    -0.06
    ifer
    -0.06
     çIJ
    -0.06
    ampion
    -0.06
    olley
    -0.06
    -driving
    -0.06
    wap
    -0.05
    POSITIVE LOGITS
     circumference
    0.07
    icode
    0.07
    icter
    0.07
    xia
    0.07
    ecut
    0.06
    onu
    0.06
    ovit
    0.06
    vro
    0.06
    idia
    0.06
    rada
    0.06
    Activations Density 0.003%

    No Known Activations