© 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. 90816
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases or symbols

    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
    ultur
    -0.06
    Ìģ
    -0.06
    ег
    -0.06
    ucher
    -0.06
    éĢı
    -0.05
    orta
    -0.05
    879
    -0.05
    periment
    -0.05
     base
    -0.05
    .transparent
    -0.05
    POSITIVE LOGITS
    ÑĢож
    0.07
    .scalablytyped
    0.07
    CEF
    0.07
    ovÃŃ
    0.07
    Ĥæķ°
    0.07
    .IsNullOr
    0.07
    ndern
    0.07
     bound
    0.07
    ابÙĦ
    0.06
    aviest
    0.06
    Activations Density 0.000%

    No Known Activations