© 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 EvalsExportsAPI 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. 128775
    Prev
    Next
    INDEX
    Explanations

    inquiries related to decision-making and evaluative processes

    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
    rete
    -0.07
    /il
    -0.07
     Props
    -0.07
    odyn
    -0.06
    alar
    -0.06
    ]={↵
    -0.06
    adesh
    -0.06
    oster
    -0.06
    ilda
    -0.06
    kehr
    -0.06
    POSITIVE LOGITS
     exact
    0.10
     depends
    0.08
     ultimate
    0.07
     actual
    0.07
     extents
    0.07
    exact
    0.07
     precise
    0.07
     ultimately
    0.06
     extent
    0.06
    ëĵł
    0.06
    Activations Density 0.033%

    No Known Activations