© 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. 2422
    Prev
    Next
    INDEX
    Explanations

    references to nickel and its various uses 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
    er
    -0.07
    eggies
    -0.07
    es
    -0.06
    s
    -0.06
    esco
    -0.06
    ema
    -0.06
    ansa
    -0.06
    asco
    -0.06
    avana
    -0.06
     Fuller
    -0.06
    POSITIVE LOGITS
    .lift
    0.08
    odem
    0.08
    ode
    0.07
    starter
    0.07
    bread
    0.07
    olas
    0.07
    CTYPE
    0.07
    lette
    0.07
    olson
    0.07
    mith
    0.07
    Activations Density 0.006%

    No Known Activations