© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 17557
    Prev
    Next
    INDEX
    Explanations

    specific brands or companies mentioned in various 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
     Gamer
    -0.07
    res
    -0.06
    Coder
    -0.06
     Agencies
    -0.06
    acer
    -0.06
    enschaft
    -0.06
    ç¾
    -0.06
    UNT
    -0.06
    unte
    -0.06
    .asp
    -0.06
    POSITIVE LOGITS
     leader
    0.11
     founder
    0.11
     director
    0.10
     president
    0.10
     owner
    0.10
     CEO
    0.10
     boss
    0.09
     President
    0.09
     chief
    0.09
     Director
    0.09
    Activations Density 0.171%

    No Known Activations