© 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. 79817
    Prev
    Next
    INDEX
    Explanations

    thoughts and feelings of concern or hesitation

    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
     Ballard
    -0.07
    TED
    -0.06
     Turnbull
    -0.06
    ales
    -0.06
    ysi
    -0.06
     sao
    -0.06
     Cougar
    -0.06
    .LayoutStyle
    -0.06
    ted
    -0.06
    ads
    -0.06
    POSITIVE LOGITS
    -details
    0.08
    ÑĢаÑħ
    0.07
     dwelling
    0.07
     dwell
    0.07
    mention
    0.07
    Fuse
    0.07
    thinkable
    0.07
    触
    0.07
    bole
    0.07
     اÙĦتÙģ
    0.07
    Activations Density 0.028%

    No Known Activations