© 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. 5-LLAMASCOPE-RES-131K
    11. 125500
    Prev
    Next
    INDEX
    Explanations

    instances of website links or URLs

    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
    iya
    -0.08
    typeparam
    -0.07
    å¿Ĺ
    -0.06
    Asc
    -0.06
    otec
    -0.06
    oval
    -0.06
    ÄĽn
    -0.06
    ynes
    -0.06
    æľŃ
    -0.06
    ovy
    -0.06
    POSITIVE LOGITS
     Canton
    0.07
    anges
    0.07
    UGH
    0.06
     equal
    0.06
    erse
    0.06
    еÑĢп
    0.06
    ners
    0.05
     Lens
    0.05
     alf
    0.05
    ÏįÏĢ
    0.05
    Activations Density 0.029%

    No Known Activations