© 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. 130660
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a range of options or sizes in a service or product 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
    iag
    -0.07
    ì²Ļ
    -0.07
    pra
    -0.06
     Ñģобой
    -0.06
    ACHI
    -0.06
    959
    -0.06
    fu
    -0.06
    reduce
    -0.06
    ampler
    -0.06
    jah
    -0.06
    POSITIVE LOGITS
     smallest
    0.11
     simple
    0.11
     tiny
    0.10
     simples
    0.10
    simple
    0.10
     small
    0.10
     single
    0.10
    single
    0.09
    ç®Ģåįķ
    0.09
    -single
    0.09
    Activations Density 0.025%

    No Known Activations