© 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. 126589
    Prev
    Next
    INDEX
    Explanations

    complex emotional themes and contrasts in character relationships

    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
    lico
    -0.07
     =
    -0.07
    ivo
    -0.06
    oven
    -0.06
    lica
    -0.06
    igo
    -0.06
    apor
    -0.06
    Ñĺ
    -0.06
    327
    -0.06
    una
    -0.06
    POSITIVE LOGITS
    ONO
    0.07
    ênh
    0.07
    ingly
    0.07
     æ¾
    0.07
    sÃŃ
    0.07
    огод
    0.07
    ERING
    0.07
    ẩn
    0.07
    ả
    0.07
    rens
    0.07
    Activations Density 0.115%

    No Known Activations