© 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. 75513
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating the end of thoughts or statements

    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
    iske
    -0.08
    inear
    -0.08
     Ả
    -0.08
    ascus
    -0.08
    اÙģت
    -0.07
    esub
    -0.07
    ÅĻeba
    -0.07
    ÑıÑĩ
    -0.07
    cobra
    -0.07
    rvé
    -0.07
    POSITIVE LOGITS
     thus
    0.18
     Thus
    0.14
     therefore
    0.14
    thus
    0.14
    Thus
    0.12
     thereby
    0.11
     hence
    0.11
     Therefore
    0.10
     so
    0.10
    æīĢ以
    0.09
    Activations Density 0.030%

    No Known Activations