© 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. 85719
    Prev
    Next
    INDEX
    Explanations

    specific measurements and instructions related to equipment for a process

    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
    ott
    -0.07
     Dysfunction
    -0.06
    edian
    -0.06
     Dup
    -0.06
    leanup
    -0.05
     Cru
    -0.05
    ite
    -0.05
    un
    -0.05
    vale
    -0.05
     Kat
    -0.05
    POSITIVE LOGITS
     Fill
    0.13
     fill
    0.13
     fills
    0.13
    -fill
    0.12
     filling
    0.12
     filled
    0.11
    fills
    0.11
    å¡«
    0.11
    Fill
    0.11
    filled
    0.10
    Activations Density 0.046%

    No Known Activations