© 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. 30966
    Prev
    Next
    INDEX
    Explanations

    recommendations and personal experiences related to gaming missions

    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
    wers
    -0.07
     Dillon
    -0.06
    ECH
    -0.06
    weeted
    -0.06
    odata
    -0.06
    stit
    -0.06
    èijī
    -0.06
    SCI
    -0.06
    è£ģ
    -0.06
    áz
    -0.06
    POSITIVE LOGITS
    ÐķС
    0.06
     timings
    0.06
    Coords
    0.06
    oot
    0.06
    .coords
    0.06
     Tir
    0.06
    FFE
    0.06
     маÑĢÑĪ
    0.06
     Sequence
    0.06
    onical
    0.06
    Activations Density 0.007%

    No Known Activations