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

    Neuronpedia

    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. 127993
    Prev
    Next
    INDEX
    Explanations

    references to "trib" and its variations, which are likely associated with tributes or tribal contexts

    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
    elic
    -0.07
    ساب
    -0.07
    trap
    -0.07
    filer
    -0.07
    stras
    -0.06
     traps
    -0.06
    nten
    -0.06
    amura
    -0.06
    ander
    -0.06
    mailer
    -0.06
    POSITIVE LOGITS
    ally
    0.08
    bed
    0.08
    ber
    0.08
    innacle
    0.08
    bons
    0.07
    ed
    0.07
    bing
    0.07
    blem
    0.07
    lox
    0.07
    ust
    0.07
    Activations Density 0.006%

    No Known Activations