© 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. 128436
    Prev
    Next
    INDEX
    Explanations

    elements related to mechanical and technological components

    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
    aud
    -0.06
     serm
    -0.06
     reflective
    -0.06
    ikk
    -0.06
    -
    -0.06
    udit
    -0.06
    ahas
    -0.06
    Bot
    -0.05
    zig
    -0.05
    '
    -0.05
    POSITIVE LOGITS
    ctrine
    0.07
    VOKE
    0.07
    onto
    0.07
    øre
    0.07
    ingo
    0.07
    립
    0.06
    incipal
    0.06
     GOODMAN
    0.06
    ckt
    0.06
    PRESSION
    0.06
    Activations Density 0.023%

    No Known Activations