© 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. 56422
    Prev
    Next
    INDEX
    Explanations

    references to specific design features or architectural components in technology-related contexts

    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
    imat
    -0.06
     mileage
    -0.06
    ìłĦìĹIJ
    -0.06
    eba
    -0.06
    Dual
    -0.06
    _rhs
    -0.06
    izu
    -0.06
    ng
    -0.06
     reserved
    -0.06
    åº
    -0.06
    POSITIVE LOGITS
     hence
    0.08
     consequently
    0.07
    olla
    0.07
    ContentLoaded
    0.07
     therefore
    0.06
    uran
    0.06
    ournal
    0.06
    OLEAN
    0.06
     idea
    0.06
     specifically
    0.06
    Activations Density 0.036%

    No Known Activations