© 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. 30421
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups affected by various situations or contexts

    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
    ĶåĽŀ
    -0.06
     Batch
    -0.06
    soever
    -0.06
    igham
    -0.06
    opp
    -0.06
     further
    -0.06
    friend
    -0.06
    ATCH
    -0.05
    WARD
    -0.05
    aml
    -0.05
    POSITIVE LOGITS
     each
    0.09
     daily
    0.09
     thousands
    0.08
     worldwide
    0.08
    each
    0.07
     annually
    0.07
    ieves
    0.07
     dollars
    0.07
    idot
    0.07
     every
    0.07
    Activations Density 0.051%

    No Known Activations