© 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. 86513
    Prev
    Next
    INDEX
    Explanations

    references to variety and distinctions among categories or groups

    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
    irk
    -0.07
    éĥİ
    -0.07
    braco
    -0.07
     Lang
    -0.06
    imli
    -0.06
    ngr
    -0.06
    egral
    -0.06
    IRC
    -0.06
    ovic
    -0.06
    à¸Ĺร
    -0.06
    POSITIVE LOGITS
     things
    0.09
    things
    0.08
     anything
    0.07
    wers
    0.07
     thing
    0.07
    anything
    0.07
     Anything
    0.06
    ustos
    0.06
    thing
    0.06
    134
    0.06
    Activations Density 0.039%

    No Known Activations