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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 96135
    Prev
    Next
    INDEX
    Explanations

    Java package imports and related code structure

    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
     Sang
    -0.06
    dale
    -0.06
    olas
    -0.05
    olit
    -0.05
    loh
    -0.05
     Cleaning
    -0.05
    onse
    -0.05
    ÙĤÙī
    -0.05
    rens
    -0.05
    .react
    -0.05
    POSITIVE LOGITS
    ibir
    0.08
    endir
    0.07
    ARING
    0.07
    imdi
    0.07
    -folder
    0.07
    -Sah
    0.07
    áš
    0.06
     بÙĦغ
    0.06
    asl
    0.06
    openh
    0.06
    Activations Density 0.003%

    No Known Activations