© 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 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. 60937
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electrical measurements and testing equipment

    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
    esson
    -0.08
    itzer
    -0.08
    lon
    -0.07
    æĮĻ
    -0.06
     baise
    -0.06
     chatte
    -0.06
    ixer
    -0.06
    ccione
    -0.06
    icari
    -0.06
     antenna
    -0.06
    POSITIVE LOGITS
    probe
    0.07
     probe
    0.07
     probes
    0.06
    UTE
    0.06
     measurement
    0.06
     Oh
    0.06
     bip
    0.06
     bread
    0.06
    elta
    0.06
    Probe
    0.06
    Activations Density 0.003%

    No Known Activations