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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5291
    Prev
    Next
    INDEX
    Explanations

    words related to ambition and goals

    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
    spiel
    -0.09
    essa
    -0.08
    inear
    -0.07
    delegate
    -0.06
    assic
    -0.06
    rupa
    -0.06
    shima
    -0.06
    arkin
    -0.06
    notice
    -0.06
    .Fat
    -0.06
    POSITIVE LOGITS
     to
    0.07
    /go
    0.07
    pt
    0.07
    lamaz
    0.07
    ноÑģÑĤÑĮ
    0.06
     loft
    0.06
     greatness
    0.06
    loff
    0.06
    äºİæĺ¯
    0.06
    ptions
    0.06
    Activations Density 0.003%

    No Known Activations