© 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. 72220
    Prev
    Next
    INDEX
    Explanations

    phrases that convey conclusions, implications, and suggestions related to public health policies and efficacy

    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
    entar
    -0.06
    issing
    -0.06
    ê´Ģ
    -0.06
    елÑİ
    -0.06
    lom
    -0.06
    eeper
    -0.06
     Ãľst
    -0.05
    linger
    -0.05
     fate
    -0.05
    )(((
    -0.05
    POSITIVE LOGITS
    uka
    0.07
    dit
    0.07
    .predict
    0.07
    oogle
    0.07
    ipy
    0.07
    UNET
    0.06
    measure
    0.06
    upro
    0.06
    warts
    0.06
    ION
    0.06
    Activations Density 0.057%

    No Known Activations