© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125325
    Prev
    Next
    INDEX
    Explanations

    descriptions or instructions related to puzzles and problem-solving activities

    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
    usalem
    -0.07
    游
    -0.06
    reon
    -0.06
    zsche
    -0.06
    alysis
    -0.06
    lsa
    -0.06
    äl
    -0.06
    reas
    -0.06
    å¾Ħ
    -0.06
    Ń
    -0.06
    POSITIVE LOGITS
    udoku
    0.08
     Sudoku
    0.08
     fox
    0.07
     sudoku
    0.07
    RowCount
    0.07
     clues
    0.07
     puzzles
    0.07
     Puzzle
    0.07
     puzzle
    0.07
    RuleContext
    0.07
    Activations Density 0.010%

    No Known Activations