© 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. 120857
    Prev
    Next
    INDEX
    Explanations

    programming functions and logical conditions within code snippets

    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
    alt
    -0.08
    ethod
    -0.07
    ardon
    -0.07
    prim
    -0.06
    gin
    -0.06
    uan
    -0.06
    utschen
    -0.06
    altet
    -0.06
    ynn
    -0.06
    	Null
    -0.06
    POSITIVE LOGITS
    è¶ħè¿ĩ
    0.10
     exceed
    0.10
     exceeds
    0.10
     пÑĢевÑĭÑĪ
    0.09
     exceeding
    0.09
     exceeded
    0.09
     below
    0.08
     greater
    0.08
    è¶ħ
    0.08
     è¶ħ
    0.08
    Activations Density 0.120%

    No Known Activations