© 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. 41560
    Prev
    Next
    INDEX
    Explanations

    prominent figures, particularly politicians and journalists, involved in current events or significant announcements

    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
    aub
    -0.07
     xong
    -0.07
    asil
    -0.07
    οκ
    -0.07
    اضر
    -0.07
     longer
    -0.06
    ANJI
    -0.06
    .dsl
    -0.06
    licative
    -0.06
    iland
    -0.06
    POSITIVE LOGITS
     said
    0.07
    IP
    0.06
    sembled
    0.06
    searchModel
    0.06
     explain
    0.06
    odash
    0.06
     doubt
    0.06
    olars
    0.06
     meanwhile
    0.06
    ç¬
    0.06
    Activations Density 0.023%

    No Known Activations