© 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 EvalsExportsAPI 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. 89309
    Prev
    Next
    INDEX
    Explanations

    first-person statements regarding personal experiences or opinions

    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
    ghan
    -0.08
    Äĥn
    -0.07
    stm
    -0.07
    ãģķãĤī
    -0.06
    aches
    -0.06
    etim
    -0.06
    etal
    -0.06
    _marshall
    -0.06
    inho
    -0.06
    emann
    -0.06
    POSITIVE LOGITS
     certainly
    0.08
    aze
    0.07
     obviously
    0.07
    lette
    0.07
     obvious
    0.06
     guess
    0.06
    .removeAll
    0.06
    andr
    0.06
     Certainly
    0.06
    libft
    0.06
    Activations Density 0.026%

    No Known Activations