© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70968
    Prev
    Next
    INDEX
    Explanations

    occurrences of the article "a" and variations of related articles or "an"

    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
    wers
    -0.09
    arsers
    -0.07
     HÃłn
    -0.07
    bs
    -0.07
    оже
    -0.07
    _UNITS
    -0.07
    immer
    -0.07
    empre
    -0.07
    ingles
    -0.07
    borg
    -0.07
    POSITIVE LOGITS
     spokesman
    0.10
     spokesperson
    0.10
     spokes
    0.09
     spokeswoman
    0.08
    licken
    0.06
     member
    0.06
    681
    0.06
    inel
    0.05
     unnamed
    0.05
     at
    0.05
    Activations Density 0.011%

    No Known Activations