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. 44118
    Prev
    Next
    INDEX
    Explanations

    words related to electrical and electronic concepts or systems

    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
    ston
    -0.21
    minster
    -0.17
    ological
    -0.15
    imedia
    -0.14
    rise
    -0.13
    fore
    -0.13
    ystone
    -0.13
    dom
    -0.13
    ibility
    -0.13
    ful
    -0.13
    POSITIVE LOGITS
    ible
    0.08
    mie
    0.07
    mr
    0.07
    leccion
    0.07
    erk
    0.06
    reib
    0.06
    mf
    0.06
    erior
    0.06
    ivr
    0.06
    orta
    0.06
    Activations Density 0.037%

    No Known Activations