© 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. 26776
    Prev
    Next
    INDEX
    Explanations

    code snippets or fragments with syntax errors

    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
    iaux
    -0.07
    reten
    -0.06
    illus
    -0.06
    eid
    -0.06
    odont
    -0.06
    steen
    -0.06
    quier
    -0.06
    quir
    -0.06
    ugin
    -0.06
    arro
    -0.06
    POSITIVE LOGITS
    Anywhere
    0.07
    ubu
    0.07
    leine
    0.07
    šov
    0.07
    ãĤ¶ãĥ¼
    0.07
    enced
    0.07
     addCriterion
    0.06
    ืà¸Ńà¸ĩ
    0.06
    owitz
    0.06
    ree
    0.06
    Activations Density 0.001%

    No Known Activations