© 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. 4205
    Prev
    Next
    INDEX
    Explanations

    requests for sharing experiences and feedback from others

    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
    Ì
    -0.06
    ause
    -0.06
    éĺ¶
    -0.05
    éīĦ
    -0.05
    eniz
    -0.05
     -
    -0.05
    aley
    -0.05
    oms
    -0.05
    Æ°Æ¡ng
    -0.05
     OT
    -0.05
    POSITIVE LOGITS
     others
    0.14
    Others
    0.13
     Others
    0.13
    others
    0.12
     fellow
    0.11
     future
    0.09
    future
    0.09
    orial
    0.09
     دÛĮگراÙĨ
    0.09
     anderen
    0.08
    Activations Density 0.022%

    No Known Activations