© 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. 58826
    Prev
    Next
    INDEX
    Explanations

    references to additional information and clarifications

    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
    Ñģклад
    -0.07
    onya
    -0.07
    aper
    -0.07
    apol
    -0.07
    ett
    -0.07
    etri
    -0.07
    ooks
    -0.07
     shovel
    -0.07
    è¾°
    -0.07
    reck
    -0.07
    POSITIVE LOGITS
    _FRAMEBUFFER
    0.06
     Nug
    0.06
    MBProgressHUD
    0.06
     Hin
    0.05
    cascade
    0.05
    797
    0.05
     Brenda
    0.05
     Contr
    0.05
    _fraction
    0.05
     Funeral
    0.05
    Activations Density 0.000%

    No Known Activations