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. 44137
    Prev
    Next
    INDEX
    Explanations

    achievements and recognition within a school or community context

    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
    áÅĻ
    -0.06
    ingleton
    -0.06
     physicist
    -0.06
    .BigDecimal
    -0.05
    igner
    -0.05
     gratuita
    -0.05
    ifen
    -0.05
     gratis
    -0.05
    족
    -0.05
    _phys
    -0.05
    POSITIVE LOGITS
     prefect
    0.12
     elected
    0.10
     pupil
    0.10
     councillors
    0.10
     captains
    0.10
     council
    0.09
     Student
    0.09
     elections
    0.09
     Peer
    0.09
     peer
    0.09
    Activations Density 0.024%

    No Known Activations