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. 43441
    Prev
    Next
    INDEX
    Explanations

    references to the letter "M" and its variations in different contexts

    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
    ubble
    -0.06
     tit
    -0.06
    addock
    -0.06
     pav
    -0.06
     lad
    -0.06
     slav
    -0.05
     Ib
    -0.05
     rem
    -0.05
    ulen
    -0.05
     Pav
    -0.05
    POSITIVE LOGITS
    niej
    0.14
    ÄĻż
    0.14
    iaÅĤ
    0.14
    iesz
    0.13
    uzu
    0.13
    iej
    0.13
    ÅĤ
    0.13
    niejs
    0.12
    ajÄħ
    0.12
    .in
    0.12
    Activations Density 0.006%

    No Known Activations