© 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. 78215
    Prev
    Next
    INDEX
    Explanations

    phrases that describe measurements or quantities related to time and effort

    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
    utto
    -0.07
    ffe
    -0.07
    oÅĪ
    -0.06
    817
    -0.06
    اÙĨت
    -0.06
     phái
    -0.06
    prit
    -0.06
    716
    -0.06
     dáv
    -0.06
    rok
    -0.06
    POSITIVE LOGITS
    éĴŁ
    0.07
    auth
    0.07
     operation
    0.07
     intense
    0.06
    ?id
    0.06
     debate
    0.06
     Prosper
    0.06
     discussion
    0.06
     prime
    0.06
     concentrated
    0.06
    Activations Density 0.016%

    No Known Activations