© 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. 17949
    Prev
    Next
    INDEX
    Explanations

    structured references or citations in academic or formal contexts

    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
    ATAL
    -0.07
    ocide
    -0.07
    mail
    -0.07
    atal
    -0.07
    asper
    -0.07
    liner
    -0.07
    sworth
    -0.07
    emailer
    -0.07
    atti
    -0.07
    755
    -0.07
    POSITIVE LOGITS
    çĬ¬
    0.06
    æ£ļ
    0.06
    .capitalize
    0.06
    ubl
    0.06
    ãĤ·ãĥ¼
    0.05
     Vig
    0.05
     Uncategorized
    0.05
    currentColor
    0.05
    ofs
    0.05
     LSB
    0.05
    Activations Density 0.003%

    No Known Activations