© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60851
    Prev
    Next
    INDEX
    Explanations

    phrases indicating authorship or active roles in processes

    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
    aled
    -0.07
    enheim
    -0.07
    wich
    -0.06
     pref
    -0.06
     posts
    -0.06
    ÑĢол
    -0.06
     Dash
    -0.06
    ädchen
    -0.06
    avel
    -0.06
    .apple
    -0.06
    POSITIVE LOGITS
    &view
    0.07
    &action
    0.07
    -appointed
    0.07
    ÏįÏĦε
    0.07
    -only
    0.06
    ÏĩÏĮ
    0.06
    apon
    0.06
     Pager
    0.06
     Partners
    0.06
    hiba
    0.06
    Activations Density 0.000%

    No Known Activations