© 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. 88908
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names

    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
    oftware
    -0.08
    adelphia
    -0.08
    phant
    -0.08
    oft
    -0.07
    eus
    -0.07
    à¥įà¤Ĺत
    -0.07
    yen
    -0.07
    aukee
    -0.07
    pane
    -0.07
    vision
    -0.07
    POSITIVE LOGITS
    -fw
    0.09
    ehler
    0.08
    .exc
    0.07
    kus
    0.07
    htt
    0.07
    zman
    0.07
    outil
    0.06
    iley
    0.06
    FF
    0.06
    ories
    0.06
    Activations Density 0.061%

    No Known Activations