© 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. 9-LLAMASCOPE-RES-131K
    11. 96602
    Prev
    Next
    INDEX
    Explanations

    references to philosophical concepts and significant figures

    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
     DropIndex
    -0.07
    .utc
    -0.07
    occo
    -0.06
    fak
    -0.06
    LEMENT
    -0.06
    身ä½ĵ
    -0.06
    .Elapsed
    -0.06
     Clips
    -0.06
    Targets
    -0.06
    åįĵ
    -0.06
    POSITIVE LOGITS
    GI
    0.07
    urette
    0.07
    338
    0.07
    URA
    0.06
    451
    0.06
    277
    0.06
    077
    0.06
    -ajax
    0.06
    .Flow
    0.06
    aten
    0.06
    Activations Density 0.001%

    No Known Activations