© 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. 9-LLAMASCOPE-RES-131K
    11. 96408
    Prev
    Next
    INDEX
    Explanations

    references to specific events and gatherings

    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
     Sabb
    -0.07
    raig
    -0.07
    олеÑĤ
    -0.07
    .exit
    -0.07
    ãĤĵãģ©
    -0.06
    SizeMode
    -0.06
    ãĥ£
    -0.06
    æ³½
    -0.06
    REW
    -0.06
    аÑĢÑĩ
    -0.06
    POSITIVE LOGITS
    oog
    0.06
     bout
    0.06
    fol
    0.06
    leness
    0.06
    ply
    0.06
    kou
    0.06
    liest
    0.06
    plies
    0.06
    implified
    0.06
    ÑĢовод
    0.05
    Activations Density 0.050%

    No Known Activations