© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90089
    Prev
    Next
    INDEX
    Explanations

    references to remembrance and honor for victims

    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
    egie
    -0.09
    outil
    -0.08
    /stdc
    -0.07
    åľ³
    -0.07
    ouden
    -0.07
    rase
    -0.07
    ierarchy
    -0.07
    ItemImage
    -0.07
    fef
    -0.07
    oulouse
    -0.07
    POSITIVE LOGITS
    ANI
    0.06
    pot
    0.06
     excell
    0.06
    spo
    0.05
    676
    0.05
    in
    0.05
     community
    0.05
     potom
    0.05
     supremacist
    0.05
    ÑĨо
    0.05
    Activations Density 0.002%

    No Known Activations