© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89774
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific phrases or words related to membership or qualifications

    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
    abay
    -0.07
    oler
    -0.06
    nett
    -0.06
    itchen
    -0.06
    akh
    -0.06
    ìĬµ
    -0.06
     Macro
    -0.06
     exh
    -0.06
     Ùħاد
    -0.06
     behalf
    -0.06
    POSITIVE LOGITS
    emy
    0.07
    OrNil
    0.07
    ÏĦικ
    0.07
    LAY
    0.07
    imator
    0.06
    _processors
    0.06
     Kund
    0.06
    agos
    0.06
    anta
    0.06
    loub
    0.06
    Activations Density 0.026%

    No Known Activations