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

    Neuronpedia

    Jacobian LensNEW
    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. 29290
    Prev
    Next
    INDEX
    Explanations

    specific prefixes or suffixes indicative of various categories or types of items

    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
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.08
    ernetes
    -0.08
    ган
    -0.08
    styleType
    -0.08
    .Generated
    -0.08
    leared
    -0.07
    ERRUPT
    -0.07
    imizer
    -0.07
    loquent
    -0.07
    elerine
    -0.07
    POSITIVE LOGITS
    ed
    0.09
    edBy
    0.08
    esco
    0.08
    åĢij
    0.08
    ãģªãĤĭ
    0.07
    们
    0.07
    ly
    0.07
    ays
    0.07
    edo
    0.07
    Ø©
    0.06
    Activations Density 0.117%

    No Known Activations