© 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. 1819
    Prev
    Next
    INDEX
    Explanations

    mentions of "walk"-related features in the description of properties

    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
    sgi
    -0.08
    944
    -0.07
    iating
    -0.07
    iates
    -0.06
    uch
    -0.06
     åĮ
    -0.06
    832
    -0.06
    æĥł
    -0.06
    utom
    -0.06
     EntityState
    -0.06
    POSITIVE LOGITS
    able
    0.08
     Learned
    0.07
     leading
    0.06
    ronic
    0.06
     indirect
    0.06
    δη
    0.06
    สาว
    0.06
    FC
    0.06
     natural
    0.06
     ticker
    0.06
    Activations Density 0.003%

    No Known Activations