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. 5581
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to medical conditions and treatments

    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
     Loren
    -0.07
    ãĤ·ãĥ¼
    -0.07
    onis
    -0.06
    anium
    -0.06
    oir
    -0.06
    _BU
    -0.06
    ksen
    -0.06
     Knights
    -0.06
     Tan
    -0.06
    ãĥĢãĥ¼
    -0.06
    POSITIVE LOGITS
    632
    0.07
    ernals
    0.07
     Lehr
    0.06
    greg
    0.06
    orts
    0.06
    acular
    0.06
    isclosed
    0.06
    egral
    0.06
    orte
    0.06
    ayah
    0.06
    Activations Density 0.082%

    No Known Activations