© 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. 106938
    Prev
    Next
    INDEX
    Explanations

    chronological or historical data references

    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
    statt
    -0.07
    /fixtures
    -0.07
    ä»ĭ
    -0.07
    æ¬ł
    -0.07
    ol
    -0.07
    ivec
    -0.07
     اÙĦبÙĦد
    -0.06
    anine
    -0.06
    agma
    -0.06
    orte
    -0.06
    POSITIVE LOGITS
    ế
    0.06
    (async
    0.06
    ickers
    0.06
    _customize
    0.06
    expire
    0.06
    anggan
    0.06
     Tick
    0.06
     Chron
    0.05
    ustos
    0.05
     Dec
    0.05
    Activations Density 0.002%

    No Known Activations