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

    Neuronpedia

    APICircuit 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. 31-LLAMASCOPE-RES-131K
    6. 44003
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "techn" and its variations, indicating a focus on technology-related terms

    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
    onte
    -0.07
    enaire
    -0.06
    رض
    -0.06
    rita
    -0.06
    ONEY
    -0.06
    time
    -0.06
    uros
    -0.06
    cntl
    -0.06
    oney
    -0.06
    TimeInterval
    -0.06
    POSITIVE LOGITS
    ological
    0.16
    ically
    0.15
    icolor
    0.14
    ologies
    0.14
    icians
    0.13
    ologically
    0.13
    iques
    0.13
    ician
    0.12
    icals
    0.12
    ocrats
    0.11
    Activations Density 0.004%

    No Known Activations