© 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. 118271
    Prev
    Next
    INDEX
    Explanations

    mentions of file or data references

    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
    enger
    -0.06
    è
    -0.06
     relief
    -0.06
    1
    -0.05
    ester
    -0.05
    i
    -0.05
    600
    -0.05
    672
    -0.05
    ento
    -0.05
    inn
    -0.05
    POSITIVE LOGITS
    chal
    0.09
     Incontri
    0.08
     consect
    0.08
     ÄĮer
    0.08
    deniz
    0.08
    iverz
    0.08
     Äijá»Ŀi
    0.08
    aylor
    0.07
    usty
    0.07
    еÑĢж
    0.07
    Activations Density 0.001%

    No Known Activations