© 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. 92455
    Prev
    Next
    INDEX
    Explanations

    conditional statements and assertions about the nature or quality of concepts

    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
    alez
    -0.07
    yster
    -0.06
    éĥİ
    -0.06
    hdl
    -0.06
    itt
    -0.06
    èĶ
    -0.06
     Pearl
    -0.06
    opensource
    -0.06
    oub
    -0.06
    imator
    -0.06
    POSITIVE LOGITS
     Garn
    0.08
     unacceptable
    0.07
    ä¸įæĺ¯
    0.07
    ãĤº
    0.07
     undesirable
    0.06
     not
    0.06
    Syn
    0.06
     dere
    0.06
     prospect
    0.06
     Prospect
    0.06
    Activations Density 0.033%

    No Known Activations