© 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. 129425
    Prev
    Next
    INDEX
    Explanations

    references to complexity and depth within artistic or narrative content

    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
    igh
    -0.07
    itur
    -0.06
    .rpc
    -0.06
    lettes
    -0.06
    alia
    -0.06
    ads
    -0.06
    ationship
    -0.06
    stery
    -0.06
    letes
    -0.06
     Cov
    -0.06
    POSITIVE LOGITS
     sheer
    0.09
     its
    0.09
    ingleton
    0.08
     rarity
    0.07
    ï¼Įå®ĥ
    0.07
    verty
    0.07
     itself
    0.07
    گار
    0.07
     context
    0.07
    å®ĥ
    0.07
    Activations Density 0.040%

    No Known Activations