© 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. 82072
    Prev
    Next
    INDEX
    Explanations

    references to event dates and locations

    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
    rella
    -0.07
    bai
    -0.07
    AILS
    -0.06
    essim
    -0.06
    andi
    -0.06
    âm
    -0.06
     corners
    -0.06
    zv
    -0.06
    aign
    -0.06
    ials
    -0.06
    POSITIVE LOGITS
    'gc
    0.07
     scalar
    0.07
     SOLD
    0.06
     TICK
    0.06
     sold
    0.06
    weg
    0.06
     tickets
    0.06
     Tickets
    0.06
    Scalar
    0.06
    åĽ£
    0.06
    Activations Density 0.011%

    No Known Activations