© 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. 3099
    Prev
    Next
    INDEX
    Explanations

    phrases and discussions that include the word "about."

    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
    izen
    -0.07
    statement
    -0.07
    Specifier
    -0.07
     statement
    -0.07
     ilgili
    -0.07
     statements
    -0.07
    _Handler
    -0.07
    '=>['
    -0.06
    ãĥĩãĥ«
    -0.06
    à¸Ķา
    -0.06
    POSITIVE LOGITS
     ways
    0.08
     Ways
    0.07
     topics
    0.06
    alous
    0.06
    907
    0.06
    ABCDEFGHIJKLMNOP
    0.06
    763
    0.06
    าà¸ĺ
    0.06
    OrFail
    0.06
    umba
    0.06
    Activations Density 0.019%

    No Known Activations