© 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. 61273
    Prev
    Next
    INDEX
    Explanations

    references to string manipulation or utilities in programming contexts

    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
    (tol
    -0.07
    зÑĥ
    -0.07
    /../
    -0.07
    ãĤ¯ãĥĪ
    -0.07
    /lg
    -0.07
    asel
    -0.07
    ìĽĥ
    -0.07
    deaux
    -0.07
    /Internal
    -0.07
    FFE
    -0.06
    POSITIVE LOGITS
    659
    0.07
     i
    0.06
     
    0.06
    igraph
    0.06
    earer
    0.06
     edition
    0.06
     sed
    0.05
    ino
    0.05
     passage
    0.05
     Commission
    0.05
    Activations Density 0.001%

    No Known Activations