© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 126457
    Prev
    Next
    INDEX
    Explanations

    references to "this" and "of" within the text

    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
     znam
    -0.07
    ovol
    -0.07
     nebu
    -0.07
    оваÑĢи
    -0.06
    воÑĢ
    -0.06
     âĹĦ
    -0.06
    oundation
    -0.06
    isto
    -0.06
    enses
    -0.06
    478
    -0.06
    POSITIVE LOGITS
    úde
    0.07
    é©
    0.06
    wipe
    0.06
    Composer
    0.06
    impse
    0.06
    idebar
    0.06
    OPS
    0.06
     page
    0.06
    losure
    0.06
    say
    0.06
    Activations Density 0.010%

    No Known Activations