© 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 EvalsExportsinterp-engineNEWAPI 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. 72380
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific characteristics or classifications of objects and entities, particularly in technical or descriptive contexts

    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
    .LookAndFeel
    -0.08
    «ĺ
    -0.07
    ¶ģ
    -0.07
     councill
    -0.07
    .scalablytyped
    -0.07
    olleyError
    -0.07
    ninger
    -0.07
    412
    -0.07
    htags
    -0.07
    ependency
    -0.06
    POSITIVE LOGITS
    anst
    0.07
     nature
    0.07
    uÄį
    0.07
    -turned
    0.07
    iid
    0.06
    ánh
    0.06
    STEM
    0.06
     hạng
    0.06
    ä¹ĭä¸Ģ
    0.06
    ozy
    0.06
    Activations Density 0.107%

    No Known Activations