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. 44055
    Prev
    Next
    INDEX
    Explanations

    characters or symbols that may indicate encoding or formatting issues

    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
    oner
    -0.06
    heits
    -0.06
    ollectors
    -0.06
    rolls
    -0.06
    olls
    -0.06
     Raised
    -0.06
    lix
    -0.06
    åıĸ
    -0.06
     seldom
    -0.06
    åIJĪ
    -0.06
    POSITIVE LOGITS
    ÅĤug
    0.17
    le
    0.09
    uta
    0.08
    Leod
    0.07
    æķ·
    0.07
    lej
    0.07
    rze
    0.07
    dou
    0.07
    ÃŃses
    0.07
    lund
    0.07
    Activations Density 0.002%

    No Known Activations