© 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. 17-LLAMASCOPE-RES-131K
    11. 92826
    Prev
    Next
    INDEX
    Explanations

    expressions of need or desire

    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
    odos
    -0.07
    ith
    -0.07
    ia
    -0.06
    ka
    -0.06
     Zah
    -0.06
    alle
    -0.06
    ically
    -0.06
    اØŃت
    -0.06
    ian
    -0.06
    hdl
    -0.06
    POSITIVE LOGITS
    ¤
    0.07
    /request
    0.06
    pell
    0.06
    ниÑĤелÑĮ
    0.06
    artner
    0.06
     à¹Ĩ
    0.06
    ched
    0.06
    çīĮ
    0.06
    414
    0.06
    AuthService
    0.06
    Activations Density 0.010%

    No Known Activations