© 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. 117476
    Prev
    Next
    INDEX
    Explanations

    the word "out" in various contexts, indicating a focus on expressions or discussions involving external perceptions or conclusions

    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
     Ying
    -0.07
    ação
    -0.06
    ä¹ĥ
    -0.06
    üst
    -0.06
    ayne
    -0.06
    theid
    -0.06
    gii
    -0.06
    ategory
    -0.06
    ÏĦÏī
    -0.06
    atican
    -0.06
    POSITIVE LOGITS
    برÛĮ
    0.07
    ermo
    0.07
     whose
    0.07
    ////////////////////////////////////////////////////////////////////////////////↵↵
    0.07
     Redistribution
    0.06
    ltr
    0.06
    .ly
    0.06
    isha
    0.06
    cka
    0.06
     Parenthood
    0.06
    Activations Density 0.004%

    No Known Activations