© 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. 70268
    Prev
    Next
    INDEX
    Explanations

    structures and frameworks for community engagement and social interaction

    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
    dda
    -0.07
    oley
    -0.06
     stores
    -0.06
    olem
    -0.06
    edm
    -0.06
    ull
    -0.06
    azon
    -0.06
    .setTo
    -0.06
    iÄħ
    -0.05
    _ALIGNMENT
    -0.05
    POSITIVE LOGITS
    formats
    0.10
     formats
    0.09
    Formats
    0.09
     format
    0.08
     formal
    0.08
     scheduling
    0.07
     FORMAT
    0.07
     sessions
    0.07
    -format
    0.07
     Yap
    0.07
    Activations Density 0.052%

    No Known Activations