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. 44115
    Prev
    Next
    INDEX
    Explanations

    requirements and mandatory elements related to 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
    ision
    -0.08
    isy
    -0.08
    exion
    -0.08
    ystack
    -0.08
    иÑģлов
    -0.07
    ázd
    -0.07
     Morav
    -0.07
    iales
    -0.07
    ission
    -0.07
     Všech
    -0.07
    POSITIVE LOGITS
    ments
    0.28
    ements
    0.20
    MENTS
    0.19
    aments
    0.17
    iments
    0.17
    lements
    0.15
    ents
    0.15
    uments
    0.15
    mens
    0.14
    éments
    0.13
    Activations Density 0.011%

    No Known Activations