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. 44220
    Prev
    Next
    INDEX
    Explanations

    phrases related to progression or motion

    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
    _BLK
    -0.06
    ebi
    -0.06
    à¥ģà¤ĸ
    -0.06
    ght
    -0.06
    eck
    -0.06
    nev
    -0.06
    CN
    -0.06
    gy
    -0.06
    icot
    -0.06
    borough
    -0.06
    POSITIVE LOGITS
     close
    0.09
     joint
    0.09
     agon
    0.09
     closest
    0.09
     level
    0.09
     goal
    0.08
     nap
    0.08
     toe
    0.08
     unbe
    0.08
     Close
    0.07
    Activations Density 0.008%

    No Known Activations