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. 22-LLAMASCOPE-RES-131K
    6. 5732
    Prev
    Next
    INDEX
    Explanations

    phrases indicating attempts to overcome challenges or obstacles

    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
    uffer
    -0.07
    isse
    -0.07
     vám
    -0.07
    ấp
    -0.07
    quier
    -0.07
     Residence
    -0.06
    chner
    -0.06
    dsn
    -0.06
    lias
    -0.06
    jte
    -0.06
    POSITIVE LOGITS
     understand
    0.08
     find
    0.08
     figure
    0.08
     cope
    0.08
     balance
    0.07
     maintain
    0.07
     stay
    0.07
    112
    0.07
     survive
    0.07
     understood
    0.07
    Activations Density 0.015%

    No Known Activations