© 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. 105193
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" followed by contextually significant phrases

    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
    Äįka
    -0.07
    illard
    -0.07
    illez
    -0.07
    owitz
    -0.07
     пÑĢом
    -0.06
    otta
    -0.06
    ëĿ¼ë§Ī
    -0.06
    å¥Ī
    -0.06
    ucch
    -0.06
    actionDate
    -0.06
    POSITIVE LOGITS
    asher
    0.06
    åĩĮ
    0.06
    ´
    0.06
    -inner
    0.06
     Hogan
    0.06
     Clayton
    0.06
    zure
    0.06
     Jaw
    0.06
     fol
    0.06
    iens
    0.06
    Activations Density 0.080%

    No Known Activations