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. 5461
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Published" and variations of it

    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
    026
    -0.07
    087
    -0.06
    deaux
    -0.06
    roys
    -0.06
    022
    -0.06
     NotFound
    -0.06
    aign
    -0.06
    ấp
    -0.06
    iod
    -0.06
    .transfer
    -0.06
    POSITIVE LOGITS
    istar
    0.08
    .fb
    0.07
    nem
    0.07
     اÙĦعربÙĬØ©
    0.06
     Maul
    0.06
    _exclude
    0.06
     pedal
    0.06
    rz
    0.06
    ACHER
    0.06
     redistribute
    0.06
    Activations Density 0.001%

    No Known Activations