© 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. 120515
    Prev
    Next
    INDEX
    Explanations

    expressions of anticipation or excitement regarding film roles

    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
    itoris
    -0.06
    iddi
    -0.06
    aza
    -0.06
     theat
    -0.06
    太éĥİ
    -0.06
    iaux
    -0.06
    eda
    -0.06
    azÄĥ
    -0.05
    nesc
    -0.05
    :selected
    -0.05
    POSITIVE LOGITS
    atÃŃm
    0.07
     character
    0.07
     continuity
    0.07
     BITTE
    0.07
    @Resource
    0.07
    character
    0.06
    nero
    0.06
     Character
    0.06
    ppe
    0.06
    uitka
    0.06
    Activations Density 0.010%

    No Known Activations