© 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. 72090
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    æ°Ķ
    -0.07
     tort
    -0.07
    èĢ³
    -0.07
     TORT
    -0.07
    ija
    -0.07
    عÙĩ
    -0.07
     Tort
    -0.06
    ãĥ©ãĥ¼
    -0.06
    LayoutManager
    -0.06
    %X
    -0.06
    POSITIVE LOGITS
     Detail
    0.07
    Detail
    0.06
    ven
    0.06
     ÑĤÑĢанÑģ
    0.05
    uster
    0.05
    é¡į
    0.05
    ]--;↵
    0.05
    ripp
    0.05
    enne
    0.05
    va
    0.05
    Activations Density 0.035%

    No Known Activations