© 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. 124964
    Prev
    Next
    INDEX
    Explanations

    references to problems and puzzles requiring solutions

    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
    isman
    -0.07
    .lex
    -0.07
    Severity
    -0.07
     ãĢĢ 
    -0.07
    meer
    -0.07
     meis
    -0.07
    ingt
    -0.07
    еÑģп
    -0.07
    .Dial
    -0.07
    (named
    -0.06
    POSITIVE LOGITS
     problem
    0.11
     problems
    0.10
     puzzle
    0.09
     mysteries
    0.09
     Problem
    0.09
     puzzles
    0.09
     Problems
    0.08
    éĹ®é¢ĺ
    0.08
    çļĦéĹ®é¢ĺ
    0.08
    problem
    0.08
    Activations Density 0.036%

    No Known Activations