© 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. 93130
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly parentheses

    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
    444
    -0.07
    ziel
    -0.06
    Intialized
    -0.06
    arget
    -0.06
    zas
    -0.06
    umhur
    -0.06
     شار
    -0.06
     Argument
    -0.06
    dım
    -0.06
    umar
    -0.06
    POSITIVE LOGITS
    ÌĨ
    0.06
    ervas
    0.06
    ScreenState
    0.06
    Fuse
    0.06
    uish
    0.05
     linkage
    0.05
    erre
    0.05
    ycop
    0.05
    ç½®
    0.05
    usion
    0.05
    Activations Density 0.000%

    No Known Activations