© 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. 58433
    Prev
    Next
    INDEX
    Explanations

    equality and truth assertions within code or configuration statements

    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
    åİħ
    -0.07
     componentDidUpdate
    -0.06
    combe
    -0.06
    wu
    -0.06
    .misc
    -0.06
    deen
    -0.06
    abajo
    -0.06
    assage
    -0.06
     ly
    -0.06
     collo
    -0.05
    POSITIVE LOGITS
     false
    0.11
     False
    0.10
    false
    0.09
    :false
    0.09
    (false
    0.08
     FALSE
    0.08
    False
    0.07
    utter
    0.07
    =false
    0.07
    VertexAttrib
    0.07
    Activations Density 0.019%

    No Known Activations