© 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. 3719
    Prev
    Next
    INDEX
    Explanations

    programming elements and code structures within the document

    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
    _Tis
    -0.07
    ebi
    -0.07
     hol
    -0.07
    سط
    -0.07
    rana
    -0.07
    vod
    -0.06
    ADDE
    -0.06
     Všech
    -0.06
    senal
    -0.06
    KW
    -0.06
    POSITIVE LOGITS
    )
    0.07
    )/
    0.07
    illery
    0.07
    abouts
    0.07
     ÙħÛĮÙĦادÛĮ
    0.07
    zych
    0.07
     Franklin
    0.07
    ago
    0.06
    usc
    0.06
    tout
    0.06
    Activations Density 0.208%

    No Known Activations