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. 43534
    Prev
    Next
    INDEX
    Explanations

    suffixes that indicate a high-stakes environment or 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
    EMENT
    -0.07
     sizes
    -0.07
    eyJ
    -0.06
    prar
    -0.06
    ERICA
    -0.06
    adiens
    -0.06
    utral
    -0.06
    .neo
    -0.06
    émon
    -0.06
     Lopez
    -0.06
    POSITIVE LOGITS
    ensity
    0.13
     stakes
    0.13
    akes
    0.13
    oltage
    0.12
    ress
    0.10
    uctose
    0.10
    stakes
    0.09
    inality
    0.09
    -profile
    0.09
     profile
    0.09
    Activations Density 0.010%

    No Known Activations