© 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. 17-LLAMASCOPE-RES-131K
    11. 57982
    Prev
    Next
    INDEX
    Explanations

    references to URLs or web domains

    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
    673
    -0.07
    674
    -0.07
    840
    -0.07
    dia
    -0.07
    isia
    -0.06
    isci
    -0.06
     favored
    -0.06
    ìĦł
    -0.06
    erc
    -0.06
    dit
    -0.06
    POSITIVE LOGITS
     Cres
    0.08
    æĢ
    0.06
    Assignable
    0.06
    /WebAPI
    0.06
    머
    0.06
    á»Ńa
    0.06
    ?v
    0.06
    ãģ
    0.06
    acionales
    0.06
    naÄį
    0.06
    Activations Density 0.003%

    No Known Activations