© 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. 117068
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving or obtaining opportunities or rewards

    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
    otte
    -0.07
    118
    -0.07
    串
    -0.07
    iyim
    -0.07
    opoulos
    -0.07
    anson
    -0.06
    afil
    -0.06
    umen
    -0.06
    inson
    -0.06
    holder
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
    rus
    0.07
    ãĤ¤ãĤ¯
    0.06
    entai
    0.06
    atro
    0.06
    ãĤ´ãĥª
    0.06
    Wiki
    0.06
     shot
    0.06
    žen
    0.06
     cors
    0.06
    Activations Density 0.028%

    No Known Activations