© 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. 62250
    Prev
    Next
    INDEX
    Explanations

    phrases related to costs and consequences associated with home maintenance

    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
     somewhat
    -0.06
     conc
    -0.06
     Merr
    -0.05
     reusable
    -0.05
    asher
    -0.05
    âĢ
    -0.05
    zer
    -0.05
    licer
    -0.05
     leftover
    -0.05
    kili
    -0.05
    POSITIVE LOGITS
     later
    0.13
    later
    0.11
     später
    0.10
    Later
    0.10
     Later
    0.09
    .Undef
    0.09
     pozdÄĽji
    0.08
    å¾Įãģ®
    0.08
    å¾Įãģ«
    0.08
     subsequently
    0.07
    Activations Density 0.017%

    No Known Activations