© 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. 15-LLAMASCOPE-RES-131K
    11. 26992
    Prev
    Next
    INDEX
    Explanations

    references to concepts of fate or destiny in various 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
    thing
    -0.08
    λÏİ
    -0.08
    ETA
    -0.07
    chez
    -0.07
    rud
    -0.07
    ç®
    -0.07
    ائ
    -0.07
    erer
    -0.07
    imits
    -0.07
    runner
    -0.07
    POSITIVE LOGITS
    fully
    0.08
    htub
    0.08
    lessly
    0.07
    ifs
    0.07
    TEGER
    0.07
    br
    0.07
    ined
    0.07
    623
    0.07
     destiny
    0.07
    inel
    0.06
    Activations Density 0.009%

    No Known Activations