© 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. 84391
    Prev
    Next
    INDEX
    Explanations

    evaluations of worth and value in various contexts

    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
     illustr
    -0.06
    pad
    -0.06
    encil
    -0.05
    ooth
    -0.05
    ån
    -0.05
    impl
    -0.05
    kest
    -0.05
    izen
    -0.05
    bt
    -0.05
     h
    -0.05
    POSITIVE LOGITS
     worth
    0.21
     Worth
    0.21
    worth
    0.19
     worthwhile
    0.13
     outweigh
    0.12
     justify
    0.11
    sworth
    0.11
     warto
    0.11
    åĢ¼
    0.10
     ÑģÑĤоиÑĤ
    0.10
    Activations Density 0.140%

    No Known Activations