© 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. 62485
    Prev
    Next
    INDEX
    Explanations

    common phrases or structures that convey various aspects of situations or narratives

    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
    atron
    -0.08
    amma
    -0.07
    roperty
    -0.07
    SURE
    -0.07
    ëħIJ
    -0.07
    TextStyle
    -0.06
     ?><?
    -0.06
    imli
    -0.06
    etag
    -0.06
    алÑİ
    -0.06
    POSITIVE LOGITS
    ÑĢÑĥ
    0.08
     odds
    0.07
     occasion
    0.07
     reason
    0.07
    weather
    0.07
    iled
    0.07
     weather
    0.06
     size
    0.06
     tamaño
    0.06
    лива
    0.06
    Activations Density 0.005%

    No Known Activations