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. 44367
    Prev
    Next
    INDEX
    Explanations

    references to countries and their statuses within political or economic 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
     Dresden
    -0.08
    avou
    -0.07
    endas
    -0.07
    dds
    -0.07
    ãĥī
    -0.07
    ersist
    -0.07
    duk
    -0.07
    xbd
    -0.07
    åŁ
    -0.07
    riday
    -0.06
    POSITIVE LOGITS
     Iceland
    0.13
     Lie
    0.11
     candidate
    0.10
     Norway
    0.10
     Candidate
    0.10
     Switzerland
    0.09
    candidate
    0.08
    Lie
    0.08
     candidates
    0.08
     Greenland
    0.08
    Activations Density 0.008%

    No Known Activations