© 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. 116881
    Prev
    Next
    INDEX
    Explanations

    mentions of historical texts and literary analysis

    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
    195
    -0.09
    184
    -0.09
    177
    -0.09
    196
    -0.08
    185
    -0.08
    goog
    -0.08
    orama
    -0.08
    197
    -0.07
     Garten
    -0.07
    181
    -0.07
    POSITIVE LOGITS
     medieval
    0.09
     Medieval
    0.09
     Hundred
    0.08
     Norman
    0.08
    121
    0.07
     Ramsey
    0.07
    eric
    0.06
    112
    0.06
     crus
    0.06
     Middle
    0.06
    Activations Density 0.065%

    No Known Activations