© 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. 57248
    Prev
    Next
    INDEX
    Explanations

    instances of the brand name "Nu" 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
    å¯Ł
    -0.07
    stab
    -0.07
    <context
    -0.07
    pta
    -0.07
    ivery
    -0.07
    adesh
    -0.07
    umbo
    -0.07
    EO
    -0.07
    strup
    -0.07
    estructor
    -0.07
    POSITIVE LOGITS
    ismatic
    0.07
    rah
    0.06
    era
    0.06
     nu
    0.06
    ÙĬدÙĬ
    0.06
    ell
    0.06
    aire
    0.06
     Král
    0.05
    лан
    0.05
    è¬
    0.05
    Activations Density 0.015%

    No Known Activations