© 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. 126275
    Prev
    Next
    INDEX
    Explanations

    instances of the word "at" and its variations in frequency

    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
    roys
    -0.07
     Miscellaneous
    -0.06
    urt
    -0.06
     Fro
    -0.06
    ovation
    -0.06
    inz
    -0.06
    owo
    -0.06
    icorn
    -0.06
    NSIndexPath
    -0.06
     McGregor
    -0.06
    POSITIVE LOGITS
     least
    0.09
    least
    0.08
     vice
    0.07
     worse
    0.07
     anyway
    0.07
     Least
    0.07
    Least
    0.07
    angep
    0.07
    yna
    0.07
     naopak
    0.07
    Activations Density 0.003%

    No Known Activations