© 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 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. 58961
    Prev
    Next
    INDEX
    Explanations

    structured programming or 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
    ro
    -0.06
    oyer
    -0.06
    cout
    -0.06
    nees
    -0.06
    the
    -0.06
    ed
    -0.06
    us
    -0.06
    ients
    -0.06
    رÙĪض
    -0.06
    pos
    -0.06
    POSITIVE LOGITS
     class
    0.09
    tiv
    0.08
    	class
    0.07
    okers
    0.07
    izyon
    0.07
    RuntimeObject
    0.07
    _$_
    0.07
    галÑĸ
    0.07
    lectron
    0.07
    _ASSUME
    0.07
    Activations Density 0.010%

    No Known Activations