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. 44120
    Prev
    Next
    INDEX
    Explanations

    specific mathematical symbols and characters typically used in equations or formulas

    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
     Peters
    -0.06
    rac
    -0.06
    ायà¤ķ
    -0.06
    ucid
    -0.06
    antha
    -0.06
    CHANNEL
    -0.06
    .nasa
    -0.06
     synthes
    -0.06
     Polic
    -0.06
    atus
    -0.06
    POSITIVE LOGITS
     cit
    0.09
     AA
    0.09
     tier
    0.09
     WG
    0.08
     tor
    0.08
     HE
    0.08
     Tier
    0.08
     APA
    0.08
     CV
    0.08
     torpedo
    0.08
    Activations Density 0.004%

    No Known Activations