© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 484
    Prev
    Next
    INDEX
    Explanations

    elements of storytelling and personal experiences

    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
    iasi
    -0.07
    ereotype
    -0.06
    ious
    -0.06
    attles
    -0.06
    ersions
    -0.05
    ë°
    -0.05
    ers
    -0.05
    867
    -0.05
    ibble
    -0.05
    ersion
    -0.05
    POSITIVE LOGITS
    ãĤ¹ãĤ¯
    0.08
    anton
    0.07
    isté
    0.07
     Stateless
    0.07
    ύ
    0.07
    UIScreen
    0.07
    orre
    0.07
     chó
    0.07
    AVED
    0.07
    æļ
    0.07
    Activations Density 0.021%

    No Known Activations