© 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. 5-LLAMASCOPE-RES-131K
    11. 125865
    Prev
    Next
    INDEX
    Explanations

    phrases indicating consequences or conditions

    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
    @nate
    -0.07
    \grid
    -0.07
    lov
    -0.07
    otal
    -0.07
    ynth
    -0.06
    angelo
    -0.06
    essim
    -0.06
    dın
    -0.06
    ssa
    -0.06
    blind
    -0.06
    POSITIVE LOGITS
    Ä±ÅŁma
    0.07
    ãĤ¤ãĤº
    0.06
    allery
    0.06
     orbit
    0.06
    леж
    0.06
    ?url
    0.06
    biased
    0.06
     ÙĪÛĮÚ©ÛĮ
    0.06
     Vig
    0.06
    ays
    0.06
    Activations Density 0.014%

    No Known Activations