© 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. 40580
    Prev
    Next
    INDEX
    Explanations

    phrases related to coding and visual results

    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
     Till
    -0.07
     Polic
    -0.07
    362
    -0.06
    erais
    -0.06
    anki
    -0.06
    梨
    -0.06
    amo
    -0.06
    .scalablytyped
    -0.06
     Loch
    -0.06
     Sinh
    -0.06
    POSITIVE LOGITS
    owi
    0.07
    dsn
    0.07
    owo
    0.07
    ãĥ³ãĥĹ
    0.07
     Hew
    0.07
     Wid
    0.07
     Ace
    0.07
     tid
    0.06
    sep
    0.06
    dw
    0.06
    Activations Density 0.038%

    No Known Activations