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

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 15842
    Prev
    Next
    INDEX
    Explanations

    punctuation and 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
    .UnitTesting
    -0.08
    uzzi
    -0.08
    롯
    -0.08
    YNAM
    -0.07
    æĬ¬
    -0.07
    alama
    -0.07
    vÄĽd
    -0.07
    elles
    -0.07
    EMPLARY
    -0.07
    geries
    -0.07
    POSITIVE LOGITS
     himself
    0.09
     statement
    0.08
    as
    0.06
     he
    0.06
    ourn
    0.06
     later
    0.06
     his
    0.06
     Statement
    0.06
    è¨Ģ
    0.06
    Pressed
    0.05
    Activations Density 0.036%

    No Known Activations