Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5754
    Prev
    Next
    INDEX
    Explanations

    phrases indicating sequences or counts of games in sports 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
    elman
    -0.07
    aller
    -0.07
    913
    -0.06
    alla
    -0.06
     four
    -0.06
    å¨
    -0.06
     ware
    -0.06
    inkle
    -0.06
    elu
    -0.06
    _IO
    -0.06
    POSITIVE LOGITS
     winning
    0.09
     win
    0.08
    ами
    0.07
    vinc
    0.07
     losing
    0.07
    éĤ¦
    0.07
    bons
    0.06
    igan
    0.06
    chedulers
    0.06
     Winning
    0.06
    Activations Density 0.002%

    No Known Activations