© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18427
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a."

    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
    itta
    -0.07
    eway
    -0.07
    ÑĩиÑħ
    -0.06
    anza
    -0.06
    boss
    -0.06
    QN
    -0.06
    ])),
    -0.06
    essor
    -0.06
    ÄĻ
    -0.06
    ิศ
    -0.06
    POSITIVE LOGITS
    744
    0.07
     Genius
    0.07
    //**↵
    0.07
     Target
    0.07
    tring
    0.07
    egan
    0.07
    usat
    0.07
     @"↵
    0.06
    Target
    0.06
    avo
    0.06
    Activations Density 0.000%

    No Known Activations