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. 43885
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of media, particularly shows and games

    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
    Mounted
    -0.07
     Baltimore
    -0.06
     Palest
    -0.06
     oslo
    -0.06
     Jerusalem
    -0.06
    ISIBLE
    -0.06
    oston
    -0.06
    Escort
    -0.06
     osp
    -0.06
    mary
    -0.06
    POSITIVE LOGITS
     Cartoon
    0.19
    Cart
    0.15
     CN
    0.14
     CART
    0.13
     Cartesian
    0.13
     Cart
    0.13
     cartoon
    0.13
     cart
    0.12
    -cart
    0.12
    .Cart
    0.12
    Activations Density 0.007%

    No Known Activations