© 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 EvalsExportsinterp-engineNEWAPI 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. 124110
    Prev
    Next
    INDEX
    Explanations

    punctuations that signify the end of a sentence

    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
    orial
    -0.06
     elsewhere
    -0.05
    ettel
    -0.05
     Silva
    -0.05
     Esp
    -0.05
    mé
    -0.05
    Esp
    -0.05
     Gamb
    -0.05
    oi
    -0.05
     borne
    -0.05
    POSITIVE LOGITS
    |
    0.07
    á»ĭ
    0.07
    itsu
    0.07
    krom
    0.07
    |RF
    0.07
     âĹĦ
    0.07
    amet
    0.07
    ilog
    0.07
    onya
    0.07
    vise
    0.06
    Activations Density 0.003%

    No Known Activations