© 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. 9-LLAMASCOPE-RES-131K
    11. 94816
    Prev
    Next
    INDEX
    Explanations

    phrases that signal references to characters or story elements in narratives

    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
    istrovstvÃŃ
    -0.09
    halb
    -0.07
    ustr
    -0.06
    atra
    -0.06
    LN
    -0.06
    ooke
    -0.06
    holm
    -0.06
    ÙĪÛĮد
    -0.06
     pending
    -0.05
    unca
    -0.05
    POSITIVE LOGITS
    oken
    0.07
    ť
    0.07
    akh
    0.07
    umpt
    0.07
    Registrar
    0.07
    西çľģ
    0.07
    pth
    0.07
    ikip
    0.07
    okens
    0.07
    ationToken
    0.06
    Activations Density 0.055%

    No Known Activations