© 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. 14874
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence structure indicators

    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
    835
    -0.06
    hausen
    -0.06
     although
    -0.06
     Fal
    -0.05
    aland
    -0.05
    iche
    -0.05
    steen
    -0.05
    ates
    -0.05
    ism
    -0.05
     capital
    -0.05
    POSITIVE LOGITS
    á»Ļ
    0.09
    ASON
    0.07
    _ASSUME
    0.07
    ëıħ
    0.07
    çłĤ
    0.07
    .exc
    0.07
    _TA
    0.07
    erview
    0.07
    olumn
    0.07
    ORB
    0.07
    Activations Density 0.006%

    No Known Activations