© 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. 82819
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names and titles

    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
    ÏĢÏĮ
    -0.06
    ace
    -0.06
    midi
    -0.06
     and
    -0.06
    ly
    -0.05
    acey
    -0.05
    ie
    -0.05
    arsity
    -0.05
    uj
    -0.05
    tp
    -0.05
    POSITIVE LOGITS
    _TA
    0.08
    пÑĢиклад
    0.08
    etim
    0.08
     meis
    0.08
    -et
    0.08
    åĥį
    0.07
     lesbi
    0.07
    Ä±ÅŁÄ±k
    0.07
    ÏĦÏģο
    0.07
     born
    0.07
    Activations Density 0.020%

    No Known Activations