© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 104375
    Prev
    Next
    INDEX
    Explanations

    verbs related to becoming aware or knowledgeable about a subject

    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
    avit
    -0.07
    jes
    -0.07
     anymore
    -0.06
    ilton
    -0.06
     missing
    -0.06
     different
    -0.06
     loops
    -0.06
     more
    -0.06
    /table
    -0.06
    chy
    -0.06
    POSITIVE LOGITS
    759
    0.08
    ypad
    0.07
    qid
    0.07
    .opendaylight
    0.06
    isode
    0.06
    PÅĻi
    0.06
    ÑĥлÑĮÑĤа
    0.06
     Sesso
    0.06
    tings
    0.06
    fans
    0.06
    Activations Density 0.018%

    No Known Activations