© 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. 93924
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to measurements and statistics

    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
    orget
    -0.07
    iso
    -0.07
    ANCH
    -0.07
    wise
    -0.06
    WISE
    -0.06
     Ini
    -0.06
     exactly
    -0.06
    наÑĩе
    -0.06
     Exactly
    -0.06
    du
    -0.06
    POSITIVE LOGITS
     sometimes
    0.15
     depending
    0.13
    sometimes
    0.11
    depending
    0.11
    ometimes
    0.11
     Sometimes
    0.10
    Sometimes
    0.09
     occasionally
    0.09
     some
    0.09
     certain
    0.08
    Activations Density 0.050%

    No Known Activations