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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3631
    Prev
    Next
    INDEX
    Explanations

    references to quantitative measures and identifiers in various contexts

    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
    nt
    -0.10
    hip
    -0.09
    ÑģÑĮ
    -0.08
    ization
    -0.08
    mente
    -0.08
    ized
    -0.08
    /or
    -0.08
    hips
    -0.08
    aire
    -0.08
    ately
    -0.08
    POSITIVE LOGITS
    amp
    0.10
    ëģĶ
    0.08
    elper
    0.08
    erea
    0.08
    advisor
    0.07
    dash
    0.07
    кÑĢаÑĹ
    0.07
    itial
    0.07
    ÑĶм
    0.07
    erty
    0.07
    Activations Density 0.165%

    No Known Activations