Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5320
    Prev
    Next
    INDEX
    Explanations

    genres and themes related to film and literature, particularly focusing on comedy, thriller, mystery, and adventure

    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
    lew
    -0.08
    chaft
    -0.07
    hlas
    -0.07
    stva
    -0.07
    ropp
    -0.06
    asso
    -0.06
     Engl
    -0.06
     regenerated
    -0.06
     persone
    -0.06
     personn
    -0.06
    POSITIVE LOGITS
     about
    0.10
     hybrid
    0.09
     hybrids
    0.09
    ybrid
    0.08
     cum
    0.08
    cum
    0.08
     involving
    0.07
    asio
    0.07
    ilha
    0.07
    about
    0.07
    Activations Density 0.029%

    No Known Activations