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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 86907
    Prev
    Next
    INDEX
    Explanations

    adverbs that modify adjectives or other adverbs, particularly those indicating a high degree of quality

    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
    ied
    -0.06
    ÐĬ
    -0.06
    olen
    -0.06
     maduras
    -0.06
    arness
    -0.06
    linkplain
    -0.06
    lobals
    -0.06
    .BorderFactory
    -0.06
    associ
    -0.05
    461
    -0.05
    POSITIVE LOGITS
     recently
    0.08
     ebenfalls
    0.08
     controversial
    0.07
    awning
    0.07
    yl
    0.07
     aforementioned
    0.07
     apt
    0.07
    ripper
    0.07
    {@
    0.07
    recent
    0.07
    Activations Density 0.034%

    No Known Activations