© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61557
    Prev
    Next
    INDEX
    Explanations

    references to assistance or availability of support

    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
    ouve
    -0.07
    offee
    -0.07
    ASH
    -0.06
    æıĽ
    -0.06
    noinspection
    -0.06
    gili
    -0.06
    боÑĤ
    -0.06
    寿
    -0.06
    singular
    -0.06
    elia
    -0.06
    POSITIVE LOGITS
     ready
    0.07
    nut
    0.07
     Gerard
    0.07
    ord
    0.07
    lain
    0.07
    /on
    0.07
    oppins
    0.07
    690
    0.06
    سÙĪب
    0.06
    lings
    0.06
    Activations Density 0.007%

    No Known Activations