© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 54036
    Prev
    Next
    INDEX
    Explanations

    elements of comparison between different groups or entities

    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
     hơi
    -0.07
    esub
    -0.07
    ÚĺÙĩ
    -0.07
    оÑĢон
    -0.07
    ãģ£ãģ
    -0.07
    eras
    -0.07
    arih
    -0.07
    overe
    -0.07
    ä¼¼ä¹İ
    -0.07
    untu
    -0.06
    POSITIVE LOGITS
     guess
    0.13
     Guess
    0.13
    Guess
    0.11
    guess
    0.10
     what
    0.08
     guesses
    0.07
    ?
    0.07
     What
    0.07
     result
    0.07
     Result
    0.07
    Activations Density 0.044%

    No Known Activations