© 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. 17-LLAMASCOPE-RES-131K
    11. 77762
    Prev
    Next
    INDEX
    Explanations

    references or citations from academic papers

    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
    uteur
    -0.09
    ael
    -0.08
    atsu
    -0.07
     zase
    -0.07
    óng
    -0.07
    Ìģt
    -0.07
    egin
    -0.07
    oe
    -0.07
    amin
    -0.07
    Äįet
    -0.07
    POSITIVE LOGITS
    622
    0.06
    478
    0.06
    yaw
    0.06
     Silk
    0.06
     version
    0.06
     Ad
    0.06
    329
    0.06
     Version
    0.06
    adelphia
    0.05
    ĥn
    0.05
    Activations Density 0.018%

    No Known Activations