© 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. 107225
    Prev
    Next
    INDEX
    Explanations

    words related to documentation and recording

    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
    atu
    -0.08
    igo
    -0.07
    cio
    -0.07
    avn
    -0.07
    erp
    -0.07
    ÄĻ
    -0.06
    å¡ŀ
    -0.06
    ape
    -0.06
    memberOf
    -0.06
    æ¼
    -0.06
    POSITIVE LOGITS
    ration
    0.07
    иÑī
    0.07
    antz
    0.07
     Mana
    0.06
    alog
    0.06
    ylim
    0.06
    Æ°u
    0.06
    krom
    0.06
    ouchers
    0.06
    odyn
    0.06
    Activations Density 0.005%

    No Known Activations