© 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. 86147
    Prev
    Next
    INDEX
    Explanations

    expressions of relationships and interactions among people

    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
    itol
    -0.07
    è
    -0.07
    adge
    -0.07
    temps
    -0.07
    adel
    -0.07
    uce
    -0.06
    ackage
    -0.06
    ainment
    -0.06
    otope
    -0.06
    _stuff
    -0.06
    POSITIVE LOGITS
     t
    0.06
     Casc
    0.06
    473
    0.06
    /workspace
    0.06
     fo
    0.06
     Packet
    0.06
     term
    0.06
     vit
    0.06
     just
    0.06
     Slee
    0.05
    Activations Density 0.071%

    No Known Activations