© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127429
    Prev
    Next
    INDEX
    Explanations

    technical terms related to advanced microscopy techniques

    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
     Ud
    -0.07
     Mixing
    -0.06
    bet
    -0.06
    jej
    -0.06
    ennie
    -0.06
    iffin
    -0.06
    PDF
    -0.06
    crud
    -0.06
    rlen
    -0.06
    mix
    -0.06
    POSITIVE LOGITS
    _probe
    0.08
    ãĤ¨ãĥ«
    0.08
     Gecko
    0.07
     movies
    0.07
     Surf
    0.07
     Byl
    0.07
    bpp
    0.07
    Probe
    0.07
    surf
    0.07
     probe
    0.06
    Activations Density 0.046%

    No Known Activations