© 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. 9-LLAMASCOPE-RES-131K
    11. 95898
    Prev
    Next
    INDEX
    Explanations

    references to brands and products in a commercial context

    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
     Desert
    -0.06
     fr
    -0.06
    uw
    -0.06
    wik
    -0.06
     dis
    -0.06
    olley
    -0.05
    è¾ħ
    -0.05
     Ling
    -0.05
     Kız
    -0.05
     desert
    -0.05
    POSITIVE LOGITS
    .nodeType
    0.07
    kin
    0.07
    imizer
    0.07
    rit
    0.07
    ager
    0.07
    iyor
    0.07
    ÑģÑĭл
    0.06
    istor
    0.06
    STITUTE
    0.06
    cts
    0.06
    Activations Density 0.022%

    No Known Activations