© 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. 15-LLAMASCOPE-RES-131K
    11. 87142
    Prev
    Next
    INDEX
    Explanations

    structured code elements, particularly class definitions and method declarations

    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
    ãģĶ
    -0.07
    تز
    -0.06
    .mj
    -0.06
    uries
    -0.06
    ucht
    -0.06
     Eld
    -0.06
    otechn
    -0.05
    undra
    -0.05
    ursor
    -0.05
    ickey
    -0.05
    POSITIVE LOGITS
    	override
    0.10
     unlike
    0.09
    overrides
    0.09
     override
    0.08
     Overrides
    0.08
     extra
    0.07
    Overrides
    0.07
    ymbol
    0.07
    _override
    0.07
    ologna
    0.07
    Activations Density 0.092%

    No Known Activations