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. 5412
    Prev
    Next
    INDEX
    Explanations

    content related to technology and its features

    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
     Jeg
    -0.07
    rais
    -0.06
     диви
    -0.06
     зави
    -0.06
    μοί
    -0.06
     INTERRUPTION
    -0.06
     огÑĢа
    -0.06
     поÑģ
    -0.06
     Ibid
    -0.06
    cess
    -0.06
    POSITIVE LOGITS
     official
    0.07
    &e
    0.07
    adic
    0.07
    akov
    0.07
     fellow
    0.07
    pong
    0.06
    member
    0.06
    kla
    0.06
    yny
    0.06
    ноÑģÑı
    0.06
    Activations Density 0.067%

    No Known Activations