© 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. 4844
    Prev
    Next
    INDEX
    Explanations

    proper nouns and historical figures

    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
    drs
    -0.08
    uco
    -0.07
    NamedQuery
    -0.07
    chten
    -0.07
    reau
    -0.07
    ordova
    -0.07
    .gov
    -0.07
    avic
    -0.07
    cae
    -0.07
    zier
    -0.07
    POSITIVE LOGITS
     II
    0.09
    инÑĥв
    0.08
     III
    0.08
     himself
    0.07
     IV
    0.06
     Humb
    0.06
     son
    0.06
     VII
    0.06
     ly
    0.06
     xứ
    0.06
    Activations Density 0.021%

    No Known Activations