© 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. 55947
    Prev
    Next
    INDEX
    Explanations

    biographical information about athletes

    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
    ená
    -0.08
    Fallback
    -0.07
    hpp
    -0.07
    urai
    -0.07
    iná
    -0.07
     ters
    -0.07
    ensus
    -0.07
    ovit
    -0.07
    ildo
    -0.07
    allet
    -0.07
    POSITIVE LOGITS
    iel
    0.06
    eea
    0.06
     caps
    0.06
    iy
    0.06
     success
    0.06
    oma
    0.05
    oya
    0.05
    ilver
    0.05
     ÑĢеп
    0.05
    γγ
    0.05
    Activations Density 0.003%

    No Known Activations