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. 5734
    Prev
    Next
    INDEX
    Explanations

    references to names and terms associated with artistic or public events

    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
    erate
    -0.06
     Brut
    -0.06
    kip
    -0.06
    kke
    -0.06
     sine
    -0.06
    i
    -0.06
    rosis
    -0.06
    ähr
    -0.06
     Refriger
    -0.06
    odge
    -0.06
    POSITIVE LOGITS
    urovision
    0.06
    íģ
    0.06
    uni
    0.06
    ãĤ«ãĥ¼
    0.06
    raq
    0.06
    ivas
    0.06
    CLU
    0.06
    stown
    0.06
    errick
    0.06
     Uni
    0.06
    Activations Density 0.001%

    No Known Activations