© 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 EvalsExportsAPI 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. 58735
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of authors and institutions

    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
    acus
    -0.07
    phins
    -0.06
    á»ī
    -0.06
    oust
    -0.06
     fragment
    -0.06
    irsch
    -0.05
    eyse
    -0.05
    PHY
    -0.05
    ekl
    -0.05
    olders
    -0.05
    POSITIVE LOGITS
     editor
    0.10
     ed
    0.09
     eds
    0.08
    (editor
    0.08
     edited
    0.07
    editor
    0.07
     editors
    0.07
     anthology
    0.07
     Editor
    0.07
     edits
    0.07
    Activations Density 0.016%

    No Known Activations