© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28898
    Prev
    Next
    INDEX
    Explanations

    references to specific years

    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
    uma
    -0.07
    armor
    -0.07
    ults
    -0.06
    lant
    -0.06
    venir
    -0.06
    егод
    -0.06
    partment
    -0.05
    ç§ĭ
    -0.05
    portion
    -0.05
    Z
    -0.05
    POSITIVE LOGITS
    .omg
    0.08
    ãģ°ãģĭãĤĬ
    0.08
    Plug
    0.07
    íĴ
    0.06
    CONDITION
    0.06
     Dav
    0.06
    ası
    0.06
     oslo
    0.06
    Extractor
    0.06
    istream
    0.06
    Activations Density 0.056%

    No Known Activations