© 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. 17236
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or processes that showcase completion or implementation

    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
    edl
    -0.07
    eltas
    -0.07
    tmpl
    -0.07
    /cmd
    -0.07
    еÑĤиÑĩ
    -0.06
     Sat
    -0.06
     belg
    -0.06
    agle
    -0.06
    .routing
    -0.06
    .Dispatch
    -0.06
    POSITIVE LOGITS
    ente
    0.09
    ark
    0.07
    amm
    0.06
    orgen
    0.06
    essage
    0.06
    ually
    0.06
    oger
    0.06
    otec
    0.06
    aminer
    0.06
    antz
    0.06
    Activations Density 0.114%

    No Known Activations