© 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 EvalsExportsAPI 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. 3503
    Prev
    Next
    INDEX
    Explanations

    words related to identity and integration

    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
    riot
    -0.07
    rud
    -0.07
    IRROR
    -0.06
    ulumi
    -0.06
    ;amp
    -0.06
    ÙĪÛĮÙĩ
    -0.06
    autoload
    -0.05
    ');"
    -0.05
    Tier
    -0.05
    .cms
    -0.05
    POSITIVE LOGITS
    ful
    0.08
    gether
    0.07
    cha
    0.07
    CHA
    0.07
     full
    0.07
    istrovstvÃŃ
    0.07
    rious
    0.07
    orno
    0.06
    ipsis
    0.06
    utton
    0.06
    Activations Density 0.001%

    No Known Activations