© 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. 125759
    Prev
    Next
    INDEX
    Explanations

    references to inaccuracies in descriptions or representations of media

    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
    onta
    -0.07
     sẻ
    -0.07
    vil
    -0.06
     Ansi
    -0.06
     tod
    -0.06
    éĥ
    -0.06
    .ns
    -0.06
    Anonymous
    -0.06
    ì¦
    -0.06
     terminal
    -0.06
    POSITIVE LOGITS
    ubber
    0.07
    exampleInputEmail
    0.06
    Ĥ¬
    0.06
     manually
    0.06
    еÑı
    0.06
    ocha
    0.06
     EntryPoint
    0.06
    langs
    0.06
     Country
    0.06
    flag
    0.06
    Activations Density 0.002%

    No Known Activations