© 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. 86336
    Prev
    Next
    INDEX
    Explanations

    information related to event ticketing and availability

    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
    opol
    -0.07
    ละ
    -0.06
    ´
    -0.06
    :host
    -0.06
    okoj
    -0.06
    ippers
    -0.06
    æ¢ħ
    -0.06
    phia
    -0.06
     ÅŁar
    -0.06
     REQUIRED
    -0.06
    POSITIVE LOGITS
     late
    0.08
    åĮ
    0.07
     Late
    0.07
     Phy
    0.07
    flows
    0.07
    orry
    0.06
    late
    0.06
    removeAttr
    0.06
    enty
    0.06
    Late
    0.06
    Activations Density 0.008%

    No Known Activations