© 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. 17-LLAMASCOPE-RES-131K
    11. 60147
    Prev
    Next
    INDEX
    Explanations

    phrases related to instruction and teaching

    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
    нимаÑĤÑĮ
    -0.09
    .radioButton
    -0.09
     olsun
    -0.08
    aad
    -0.08
    '],$
    -0.08
    ло
    -0.07
    ãĤĬãģ¨
    -0.07
    ãĥĩãĤ£ãĤ¢
    -0.07
    ูà¹Ħ
    -0.07
    ượt
    -0.07
    POSITIVE LOGITS
    ,
    0.17
    ,↵
    0.10
    ,↵↵
    0.10
     ,
    0.08
    à¥ĭà¤Ĥ,
    0.08
    à¥ĭ,
    0.08
    ा,
    0.07
    ormal
    0.07
    à¹Į,
    0.07
    ird
    0.07
    Activations Density 0.491%

    No Known Activations