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. 43395
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters commonly used in textual representations or formatting

    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
     (?)
    -0.08
     ðŁij
    -0.08
     haha
    -0.07
     (#
    -0.07
     kinda
    -0.07
     instagram
    -0.07
     (?
    -0.07
     âĢª
    -0.07
     (=
    -0.07
    orda
    -0.07
    POSITIVE LOGITS
     Teh
    0.08
     lj
    0.07
     Horde
    0.07
     fandom
    0.07
     Mistress
    0.07
     Urs
    0.07
     weblog
    0.06
    fic
    0.06
    .live
    0.06
     Goddess
    0.06
    Activations Density 0.010%

    No Known Activations