© 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. 22-LLAMASCOPE-RES-131K
    11. 3822
    Prev
    Next
    INDEX
    Explanations

    statements that assert or emphasize the obvious or prevalent assumptions about situations

    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
    currently
    -0.08
     soon
    -0.08
    getti
    -0.08
    fono
    -0.08
    yah
    -0.07
    opis
    -0.07
    esser
    -0.07
     célib
    -0.07
    ataire
    -0.07
    mutable
    -0.07
    POSITIVE LOGITS
     inevitable
    0.07
    nt
    0.07
     yesterday
    0.07
     predictable
    0.06
     fun
    0.06
    rogen
    0.06
     necessary
    0.06
     meant
    0.06
     inev
    0.06
     foreseeable
    0.05
    Activations Density 0.045%

    No Known Activations