© 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 EvalsExportsinterp-engineNEWAPI 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. 86350
    Prev
    Next
    INDEX
    Explanations

    expressions emphasizing significance or necessity

    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
     Wonder
    -0.06
    AuthProvider
    -0.06
     Marcos
    -0.06
    afari
    -0.06
    arden
    -0.06
    onde
    -0.06
    iteli
    -0.06
    Ĩ
    -0.06
    atos
    -0.06
    odos
    -0.06
    POSITIVE LOGITS
    ÃŃo
    0.07
    MES
    0.06
    abyte
    0.06
    Verdana
    0.06
     Palmer
    0.06
     ìĹŃ
    0.06
    ies
    0.06
    imony
    0.06
    estroy
    0.06
    ollower
    0.06
    Activations Density 0.008%

    No Known Activations