© 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. 106282
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or advice

    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
    ates
    -0.06
    ottie
    -0.06
    ’
    -0.06
    pers
    -0.06
    170
    -0.05
     sphere
    -0.05
     Revenge
    -0.05
     unless
    -0.05
    pick
    -0.05
     counter
    -0.05
    POSITIVE LOGITS
     appreciated
    0.08
     å©
    0.07
     Bryant
    0.07
    nahme
    0.07
    aintenance
    0.07
    __.__
    0.07
    egin
    0.07
    usi
    0.07
    füh
    0.07
    麻
    0.07
    Activations Density 0.003%

    No Known Activations