© 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. 87377
    Prev
    Next
    INDEX
    Explanations

    numerical and technical specifications related to software and gaming

    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
     crow
    -0.05
    _FOLDER
    -0.05
    ±
    -0.05
     "
    -0.05
     T
    -0.05
    g
    -0.05
     versus
    -0.05
    lat
    -0.05
     duck
    -0.05
     d
    -0.05
    POSITIVE LOGITS
    -addon
    0.08
    Ctrls
    0.08
    nici
    0.08
    rador
    0.08
     Phát
    0.07
    -archive
    0.07
    ÎłÏģο
    0.07
     jadx
    0.07
    Ïģαν
    0.07
    å¥Ī
    0.07
    Activations Density 0.001%

    No Known Activations