© 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. 105977
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically the period

    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
    .scalablytyped
    -0.08
    idot
    -0.07
    /umd
    -0.07
     Báo
    -0.07
    мÑĸнÑĸ
    -0.07
    леÑĤ
    -0.07
    _NT
    -0.07
    оÑĢоÑĤ
    -0.07
    iez
    -0.07
    indow
    -0.06
    POSITIVE LOGITS
    qu
    0.07
     hob
    0.06
    861
    0.06
    rit
    0.06
    547
    0.06
     postings
    0.06
    QU
    0.06
    Kit
    0.05
    mai
    0.05
     writ
    0.05
    Activations Density 0.000%

    No Known Activations