© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 26653
    Prev
    Next
    INDEX
    Explanations

    punctuation or conjunctions within complex sentences

    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
    optgroup
    -0.08
    udio
    -0.07
    adio
    -0.06
     connexion
    -0.06
     disgust
    -0.06
    awi
    -0.06
    aN
    -0.06
     ÐĴики
    -0.06
    sworth
    -0.05
    igan
    -0.05
    POSITIVE LOGITS
     taraf
    0.07
    icari
    0.07
    ãĥ³ãĤ¯
    0.07
    ÙħاÙĦ
    0.07
     our
    0.07
    udent
    0.06
     ours
    0.06
     bize
    0.06
    ãĥªãĥ¼
    0.06
     saya
    0.06
    Activations Density 0.018%

    No Known Activations