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. 5722
    Prev
    Next
    INDEX
    Explanations

    specific descriptors and characteristics related to people and places in a narrative context

    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
    ãĥĽãĥĨãĥ«
    -0.06
     hospitals
    -0.06
     hotels
    -0.06
    resas
    -0.06
     Dinner
    -0.06
    bef
    -0.06
     Contract
    -0.06
     meal
    -0.06
    ÄĻd
    -0.06
     Hospitals
    -0.06
    POSITIVE LOGITS
     counter
    0.22
    counter
    0.19
    -counter
    0.19
     Counter
    0.19
    Counter
    0.18
     counters
    0.17
    _counter
    0.15
    .counter
    0.15
    (counter
    0.15
    ounter
    0.14
    Activations Density 0.086%

    No Known Activations