© 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. 15-LLAMASCOPE-RES-131K
    11. 87252
    Prev
    Next
    INDEX
    Explanations

    quotes and dialogue in the text

    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
    ellido
    -0.07
    ogg
    -0.07
    iosper
    -0.07
     åıĮ线
    -0.07
     vidé
    -0.07
    iš
    -0.07
    $LANG
    -0.07
    .processor
    -0.06
    localctx
    -0.06
    olie
    -0.06
    POSITIVE LOGITS
    657
    0.06
    ãĤ¤ãĥī
    0.06
    eltas
    0.06
    زر
    0.05
    ì°©
    0.05
     KeyValue
    0.05
    473
    0.05
    ì¶ľ
    0.05
     Bear
    0.05
    autiful
    0.05
    Activations Density 0.062%

    No Known Activations