© 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. 77147
    Prev
    Next
    INDEX
    Explanations

    references to age, categorization, and publication details

    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
    RD
    -0.07
     Nikola
    -0.06
     including
    -0.06
     Hor
    -0.06
     ko
    -0.06
    angel
    -0.06
     Erd
    -0.05
     Sadd
    -0.05
    307
    -0.05
     microwave
    -0.05
    POSITIVE LOGITS
    thon
    0.08
    ufs
    0.08
    subcategory
    0.07
     altında
    0.07
    uja
    0.07
    orrent
    0.07
     겨
    0.07
    ATUS
    0.07
    CHASE
    0.07
     detr
    0.07
    Activations Density 0.006%

    No Known Activations