© 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. 27870
    Prev
    Next
    INDEX
    Explanations

    references to individuals' actions and interactions

    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
    ثار
    -0.07
     infer
    -0.06
    kich
    -0.06
    interop
    -0.06
     Fa
    -0.06
    uko
    -0.06
    xes
    -0.06
     ^↵
    -0.06
    catid
    -0.06
    ɵ
    -0.06
    POSITIVE LOGITS
     can
    0.23
    åı¯ä»¥
    0.18
    can
    0.16
     could
    0.15
     able
    0.14
     ÙĬÙħÙĥÙĨ
    0.14
    สามารà¸ĸ
    0.14
    èĥ½å¤Ł
    0.14
    Can
    0.13
    .can
    0.13
    Activations Density 0.124%

    No Known Activations