Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5445
    Prev
    Next
    INDEX
    Explanations

    concepts related to ethics and societal values

    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
     vert
    -0.07
    ìĽIJìĿ´
    -0.07
    vor
    -0.06
    anol
    -0.06
     sched
    -0.06
     tir
    -0.06
     Prix
    -0.06
     âľ
    -0.06
    íĤ
    -0.06
    esp
    -0.06
    POSITIVE LOGITS
     поÑģÑĤÑĥп
    0.06
    isclosed
    0.06
    OSC
    0.06
    ?action
    0.06
    lue
    0.06
    existent
    0.06
     Freund
    0.06
    osit
    0.06
     Moment
    0.06
    icrosoft
    0.06
    Activations Density 0.027%

    No Known Activations