© 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. 30623
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the allocation or distribution of resources or parameters

    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
    inion
    -0.07
     Wilkinson
    -0.06
     FileInfo
    -0.06
    yr
    -0.06
    iros
    -0.05
    Todd
    -0.05
     Entries
    -0.05
    istung
    -0.05
    alli
    -0.05
    esini
    -0.05
    POSITIVE LOGITS
     each
    0.16
    each
    0.13
     Each
    0.12
     EACH
    0.12
    Each
    0.12
     каждÑĭй
    0.11
     cada
    0.11
     кажд
    0.11
     каждого
    0.10
    .each
    0.10
    Activations Density 0.023%

    No Known Activations