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. 5393
    Prev
    Next
    INDEX
    Explanations

    names of ballet companies and orchestras

    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
    asha
    -0.09
    rve
    -0.07
    oui
    -0.07
    deo
    -0.06
    οÏħÏĤ
    -0.06
    .hl
    -0.06
    ç±³
    -0.06
    ampa
    -0.06
    ="{!!
    -0.06
    sled
    -0.06
    POSITIVE LOGITS
     sym
    0.11
    Sym
    0.10
     chamber
    0.10
     Symphony
    0.10
     Chamber
    0.09
     Sym
    0.09
    _sym
    0.09
     Phil
    0.08
     Opera
    0.08
     String
    0.08
    Activations Density 0.013%

    No Known Activations