© 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. 89297
    Prev
    Next
    INDEX
    Explanations

    references to programs, applications, and various award-related events

    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
    ascar
    -0.08
    abee
    -0.07
    ebin
    -0.07
    occo
    -0.07
    unami
    -0.07
    عات
    -0.06
    žÃŃ
    -0.06
    sein
    -0.06
    anean
    -0.06
    rips
    -0.06
    POSITIVE LOGITS
     selections
    0.09
     Selection
    0.09
     selection
    0.09
     batch
    0.08
    selection
    0.08
    Selection
    0.08
    -selection
    0.08
     selected
    0.07
    _Selection
    0.07
    (selection
    0.07
    Activations Density 0.056%

    No Known Activations