© 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. 86603
    Prev
    Next
    INDEX
    Explanations

    references to the Kiribati region or related geographical topics

    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
    ãĥ³ãĤ°
    -0.07
    ing
    -0.06
    ed
    -0.06
    eld
    -0.05
    tica
    -0.05
    ingt
    -0.05
    kap
    -0.05
    yg
    -0.05
    erty
    -0.05
     adversity
    -0.05
    POSITIVE LOGITS
    patrick
    0.12
    ezi
    0.08
    illow
    0.08
    ehler
    0.08
    asic
    0.07
    ály
    0.07
    linger
    0.07
    sey
    0.07
    ataka
    0.07
    folio
    0.07
    Activations Density 0.008%

    No Known Activations