© 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. 27830
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the existence or availability of specific items or conditions

    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
    svc
    -0.07
     hereby
    -0.07
    baugh
    -0.07
     quite
    -0.07
    /stretch
    -0.07
    .until
    -0.06
     rất
    -0.06
    tec
    -0.06
    zc
    -0.06
    è¬Ŀ
    -0.06
    POSITIVE LOGITS
     anything
    0.07
     any
    0.07
     ANY
    0.07
     вдÑĢÑĥг
    0.07
     pending
    0.07
    any
    0.07
     suddenly
    0.07
    aeper
    0.07
    anything
    0.07
    ëĿ¼ëıĦ
    0.06
    Activations Density 0.017%

    No Known Activations