© 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. 15-LLAMASCOPE-RES-131K
    11. 88578
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the lack of difficulty or limitations

    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
    ISMATCH
    -0.08
    777
    -0.08
    egan
    -0.08
    ÑģÑİ
    -0.07
    .appspot
    -0.07
    ãģĬãĤĬ
    -0.07
    setItem
    -0.07
    .si
    -0.07
    ScrollIndicator
    -0.07
    رخ
    -0.07
    POSITIVE LOGITS
     regard
    0.11
     ado
    0.09
     help
    0.07
     regards
    0.07
     further
    0.06
     complaint
    0.06
     consideration
    0.06
    ouri
    0.06
    thers
    0.06
     reference
    0.06
    Activations Density 0.016%

    No Known Activations