© 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. 84273
    Prev
    Next
    INDEX
    Explanations

    inquiries about products or services

    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
    orio
    -0.06
    ORIES
    -0.06
    roscope
    -0.06
    ories
    -0.06
    оÑĢом
    -0.06
    herits
    -0.06
    adar
    -0.06
    iquement
    -0.06
     Cumhur
    -0.06
     FITNESS
    -0.06
    POSITIVE LOGITS
    æģ
    0.07
    _proba
    0.07
    ames
    0.07
    oin
    0.07
    odo
    0.06
     Guns
    0.06
    å·±
    0.06
    endif
    0.06
     nackte
    0.06
    PAY
    0.06
    Activations Density 0.000%

    No Known Activations