© 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. 55558
    Prev
    Next
    INDEX
    Explanations

    references to purchasing experiences and product deals

    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
    ccione
    -0.08
    __.__
    -0.07
     conc
    -0.06
    ÑĦÑĦ
    -0.06
    utch
    -0.06
     Holden
    -0.06
    ÑĢоÑĪ
    -0.06
    longleftrightarrow
    -0.06
    vise
    -0.06
     tender
    -0.06
    POSITIVE LOGITS
     item
    0.11
     items
    0.10
     products
    0.10
     ITEM
    0.09
     Item
    0.09
     Items
    0.08
    item
    0.08
    -item
    0.08
    items
    0.08
     product
    0.08
    Activations Density 0.032%

    No Known Activations