© 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. 93770
    Prev
    Next
    INDEX
    Explanations

    references to the author Lovasz

    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
    ibt
    -0.08
    ivas
    -0.07
    esimal
    -0.06
    578
    -0.06
    Wir
    -0.06
    .scalablytyped
    -0.06
     ëı
    -0.06
    ìĹĶ
    -0.06
    486
    -0.06
     CreateMap
    -0.06
    POSITIVE LOGITS
    /lo
    0.08
    ξι
    0.07
    онÑĮ
    0.07
    ohl
    0.07
    ettel
    0.07
    renc
    0.07
    omba
    0.07
    ç´ļ
    0.07
    tech
    0.07
    ullo
    0.07
    Activations Density 0.005%

    No Known Activations