© 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. 61334
    Prev
    Next
    INDEX
    Explanations

    references to authority or institutional 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
    emez
    -0.09
    بÙĪاسطة
    -0.09
    maal
    -0.08
    #af
    -0.08
    zeÅĪ
    -0.08
    .scalablytyped
    -0.08
    #ac
    -0.08
    ewan
    -0.08
    .epam
    -0.08
    foon
    -0.08
    POSITIVE LOGITS
    error
    0.05
    (s
    0.05
     McCl
    0.05
    iri
    0.05
     Neo
    0.05
    ims
    0.05
     Mari
    0.05
    ears
    0.05
    bb
    0.05
    ym
    0.05
    Activations Density 0.132%

    No Known Activations