© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 127591
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or organizations

    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
    OffsetTable
    -0.09
    سة
    -0.08
    arResult
    -0.07
    okud
    -0.07
    anja
    -0.07
    optic
    -0.07
    tual
    -0.07
    -animate
    -0.07
    .builders
    -0.07
     GOODMAN
    -0.07
    POSITIVE LOGITS
     lore
    0.08
    mania
    0.07
    ’s
    0.07
     fame
    0.07
    's
    0.06
    1
    0.06
    sworth
    0.06
    enet
    0.06
     ail
    0.06
     mode
    0.06
    Activations Density 0.380%

    No Known Activations