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. 43508
    Prev
    Next
    INDEX
    Explanations

    references to various types of automated systems or robots

    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
    hape
    -0.06
    ieves
    -0.06
    :view
    -0.06
    hire
    -0.06
    hair
    -0.06
    holds
    -0.06
    ustain
    -0.06
    hurst
    -0.06
    <context
    -0.06
    _subtype
    -0.06
    POSITIVE LOGITS
    ched
    0.19
    ching
    0.14
    CHED
    0.14
    ches
    0.14
    chy
    0.12
    ch
    0.11
    chers
    0.11
    cher
    0.10
    ulin
    0.10
    ul
    0.09
    Activations Density 0.004%

    No Known Activations