© 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. 72130
    Prev
    Next
    INDEX
    Explanations

    punctuation and its placement within 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
    .newBuilder
    -0.06
    ëĿ¼ëıĦ
    -0.06
    lok
    -0.06
     precedence
    -0.06
    umblr
    -0.06
     will
    -0.06
    osl
    -0.06
    will
    -0.06
     prere
    -0.06
    à¹Ģà¸ķร
    -0.05
    POSITIVE LOGITS
     now
    0.20
    now
    0.17
     ÑĤепеÑĢÑĮ
    0.15
    -now
    0.15
    çİ°åľ¨
    0.14
     ahora
    0.14
     Now
    0.14
    _now
    0.13
    Now
    0.13
     subsequent
    0.13
    Activations Density 0.071%

    No Known Activations