© 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. 17279
    Prev
    Next
    INDEX
    Explanations

    patterns of dialogue or quotation marks indicating speech or direct quotes

    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
    anson
    -0.06
    -material
    -0.06
    θεν
    -0.06
    unde
    -0.06
    alt
    -0.06
    yster
    -0.05
     Material
    -0.05
     Forg
    -0.05
     material
    -0.05
     hypnot
    -0.05
    POSITIVE LOGITS
     Nope
    0.11
    ailable
    0.09
    ıcı
    0.09
     WRONG
    0.08
    æ®Ĭ
    0.08
     untrue
    0.08
     Hog
    0.08
    .scalablytyped
    0.07
    WR
    0.07
    entionPolicy
    0.07
    Activations Density 0.018%

    No Known Activations