© 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. 9-LLAMASCOPE-RES-131K
    6. 95259
    Prev
    Next
    INDEX
    Explanations

    references to vehicle models and their specifications

    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
    avy
    -0.08
    .opend
    -0.07
     Proud
    -0.06
    aper
    -0.06
    irst
    -0.06
    ipped
    -0.06
    æľ
    -0.06
    awy
    -0.06
    æijĩ
    -0.05
    ane
    -0.05
    POSITIVE LOGITS
    UnderTest
    0.08
    xcf
    0.08
    TURE
    0.08
    Mage
    0.08
    ÛĮزÛĮ
    0.07
    LinkId
    0.07
    mux
    0.07
     ÑĢÑĸвенÑĮ
    0.07
    massage
    0.07
    Slf
    0.07
    Activations Density 0.009%

    No Known Activations