© 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. 17-LLAMASCOPE-RES-131K
    6. 41297
    Prev
    Next
    INDEX
    Explanations

    statistical information and numerical data

    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
    orra
    -0.07
    este
    -0.07
    iest
    -0.06
    orts
    -0.06
    Òij
    -0.06
    ÂĢÂĻ
    -0.06
    ificent
    -0.06
     anywhere
    -0.06
    toMatch
    -0.06
    occo
    -0.06
    POSITIVE LOGITS
    .asc
    0.07
    icut
    0.06
    atas
    0.06
    yre
    0.06
    ãĥ¼ãĤº
    0.06
    theid
    0.06
    cmc
    0.06
     zdrav
    0.06
    oleon
    0.06
    моÑĤ
    0.06
    Activations Density 0.001%

    No Known Activations