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. 44040
    Prev
    Next
    INDEX
    Explanations

    numerical values and version identifiers

    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
    acier
    -0.07
     the
    -0.07
     number
    -0.07
     de
    -0.07
     men
    -0.06
     side
    -0.06
     second
    -0.06
     post
    -0.06
     small
    -0.06
     h
    -0.06
    POSITIVE LOGITS
    .
    0.12
    .xx
    0.10
    dot
    0.10
    _dot
    0.09
    \\.
    0.09
    -dot
    0.09
    .X
    0.08
    .%
    0.08
    _DOT
    0.08
    _RC
    0.08
    Activations Density 0.014%

    No Known Activations