© 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. 92823
    Prev
    Next
    INDEX
    Explanations

    the various forms of the verb "use" in different contexts

    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
    ĥ
    -0.06
    fon
    -0.06
    toy
    -0.06
    lıģına
    -0.06
    eing
    -0.06
    printer
    -0.06
    chia
    -0.06
    cion
    -0.06
    PRESS
    -0.06
    ignet
    -0.06
    POSITIVE LOGITS
     to
    0.13
     Äijá»ĥ
    0.10
    .scalablytyped
    0.07
    vÄĽÅĻ
    0.07
    gnore
    0.07
     ÑĩÑĤобÑĭ
    0.07
    	to
    0.07
    activex
    0.07
     Ritch
    0.07
    ToSend
    0.07
    Activations Density 0.027%

    No Known Activations