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. 43731
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate presence 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
    ục
    -0.07
    -eslint
    -0.06
    adders
    -0.06
    utches
    -0.06
    RuntimeObject
    -0.06
     consultation
    -0.06
    ategory
    -0.05
    aÄį
    -0.05
    Builders
    -0.05
    /categories
    -0.05
    POSITIVE LOGITS
    herent
    0.12
     ourselves
    0.11
    extr
    0.10
    -between
    0.10
     us
    0.10
     oneself
    0.10
    between
    0.09
    here
    0.09
     faces
    0.09
    express
    0.09
    Activations Density 0.055%

    No Known Activations