© 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. 87841
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'N' and its variations in the context of names or proper nouns

    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
     Fal
    -0.06
    thew
    -0.06
     nip
    -0.06
     Gardner
    -0.06
     Codec
    -0.06
    fare
    -0.05
    iguous
    -0.05
    eries
    -0.05
     Airways
    -0.05
    :eq
    -0.05
    POSITIVE LOGITS
     born
    0.08
    islav
    0.07
    athon
    0.07
     ÑĢождениÑı
    0.07
    اÛĮØ´
    0.07
    abouts
    0.07
    ulton
    0.07
    ncy
    0.07
    //{{
    0.07
    ermo
    0.07
    Activations Density 0.000%

    No Known Activations