© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 83922
    Prev
    Next
    INDEX
    Explanations

    words related to qualifications and the concept of qualifying

    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
    apan
    -0.07
    ç±į
    -0.07
    aliz
    -0.07
    esel
    -0.07
    ese
    -0.06
    Ø©
    -0.06
    asel
    -0.06
    ETO
    -0.06
    org
    -0.06
    alc
    -0.06
    POSITIVE LOGITS
    ÑģÑĮ
    0.08
    /lic
    0.08
    aroo
    0.08
    ubit
    0.07
    atory
    0.07
    ео
    0.07
    quential
    0.07
    itative
    0.07
    ubes
    0.07
    á»ģn
    0.07
    Activations Density 0.011%

    No Known Activations