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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 93834
    Prev
    Next
    INDEX
    Explanations

    qualifiers related to credibility and discernment

    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
     Sims
    -0.06
     bah
    -0.06
    bah
    -0.06
    -packages
    -0.06
    .IsEmpty
    -0.06
    mlink
    -0.06
     Lar
    -0.06
    kus
    -0.06
    ιά
    -0.06
    arity
    -0.05
    POSITIVE LOGITS
     serious
    0.12
     sane
    0.11
     worth
    0.11
     Worth
    0.10
     Serious
    0.10
     decent
    0.10
     sensible
    0.09
    serious
    0.09
     true
    0.09
    proper
    0.09
    Activations Density 0.117%

    No Known Activations