© 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 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. 17-LLAMASCOPE-RES-131K
    11. 126678
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Learn" and its variations, signifying education or opportunities for acquisition of knowledge

    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
    nut
    -0.08
    rouch
    -0.08
    gle
    -0.08
    anyak
    -0.07
    yll
    -0.07
    Ñģклад
    -0.07
    аÑĢаÑĤ
    -0.07
    à¸Ħล
    -0.07
    cala
    -0.06
    stan
    -0.06
    POSITIVE LOGITS
    ings
    0.12
    Ĺ
    0.07
    ies
    0.06
    INGS
    0.06
    ers
    0.06
    hardt
    0.06
    iane
    0.06
    ingo
    0.06
    ÂŃing
    0.06
    lng
    0.06
    Activations Density 0.006%

    No Known Activations