© 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. 76496
    Prev
    Next
    INDEX
    Explanations

    references to photography and nature

    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
    á»Ĩ
    -0.09
    رÙĩ
    -0.07
    arah
    -0.06
    idla
    -0.06
    å§
    -0.06
     ç¯
    -0.06
    áty
    -0.06
    ke
    -0.06
    ardo
    -0.06
    änge
    -0.06
    POSITIVE LOGITS
    rams
    0.07
     equ
    0.06
    .flash
    0.06
    asz
    0.06
    ico
    0.06
    cox
    0.06
    asted
    0.06
    urn
    0.06
    anie
    0.06
    eneric
    0.06
    Activations Density 0.000%

    No Known Activations