© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89733
    Prev
    Next
    INDEX
    Explanations

    sentence endings with punctuation marks

    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
    cken
    -0.07
    ainen
    -0.07
    .fm
    -0.07
    heits
    -0.07
    ìłĿ
    -0.07
    ginas
    -0.07
    ÙĪØ²Ùĩ
    -0.07
    eniz
    -0.06
    itters
    -0.06
    ankan
    -0.06
    POSITIVE LOGITS
     another
    0.07
     also
    0.07
     even
    0.07
     alongside
    0.07
    -react
    0.06
    è¿ĺæľī
    0.06
     cũng
    0.06
     Also
    0.06
     Another
    0.06
     же
    0.06
    Activations Density 0.017%

    No Known Activations