© 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. 82679
    Prev
    Next
    INDEX
    Explanations

    phrases and words associated with totality or completeness

    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
    -offs
    -0.06
    offs
    -0.06
    ictim
    -0.06
    766
    -0.06
    xious
    -0.06
    nze
    -0.06
    ford
    -0.06
    838
    -0.06
    гоÑĢод
    -0.06
    íĥĿ
    -0.06
    POSITIVE LOGITS
     everything
    0.07
     all
    0.07
    axon
    0.07
     stuff
    0.07
    uju
    0.06
    AllWindows
    0.06
    okit
    0.06
    endale
    0.06
     pk
    0.06
    urement
    0.06
    Activations Density 0.048%

    No Known Activations