© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88337
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating the end of sentences

    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
    atha
    -0.07
    /Branch
    -0.07
    ntl
    -0.07
    Filed
    -0.07
    Plan
    -0.07
    CellStyle
    -0.07
    roller
    -0.07
    ACHE
    -0.07
    assel
    -0.06
    ardy
    -0.06
    POSITIVE LOGITS
     spokeswoman
    0.07
     its
    0.06
     they
    0.06
    733
    0.06
     leading
    0.06
     while
    0.06
     opposite
    0.06
    peon
    0.06
    yr
    0.06
    ýn
    0.06
    Activations Density 0.029%

    No Known Activations