© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76953
    Prev
    Next
    INDEX
    Explanations

    references to testing frameworks in programming 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
    letic
    -0.07
    lical
    -0.07
    onga
    -0.07
    óng
    -0.07
    zym
    -0.06
    roker
    -0.06
    blo
    -0.06
    anja
    -0.06
    angi
    -0.06
    zac
    -0.06
    POSITIVE LOGITS
    mue
    0.07
    y
    0.07
    оÑıн
    0.07
    Ļ
    0.06
    ียà¸ģ
    0.06
    aç
    0.06
    .fun
    0.06
     harm
    0.06
     PIO
    0.06
    ³
    0.06
    Activations Density 0.000%

    No Known Activations