© 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. 104782
    Prev
    Next
    INDEX
    Explanations

    specific punctuation marks and their placement in relation to sentences and clauses

    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
    ycler
    -0.06
    pip
    -0.06
    isposable
    -0.06
    acin
    -0.06
    nie
    -0.06
    Ñĥже
    -0.06
     already
    -0.05
     incl
    -0.05
     unto
    -0.05
    åŁ
    -0.05
    POSITIVE LOGITS
    Alternatively
    0.08
     Alternatively
    0.08
     Altern
    0.07
    £
    0.07
    å¿
    0.07
    à¹īà¸Ńà¸Ļ
    0.07
    _ALWAYS
    0.07
    inding
    0.07
    altern
    0.07
     altern
    0.07
    Activations Density 0.013%

    No Known Activations