© 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. 74412
    Prev
    Next
    INDEX
    Explanations

    components related to visual and graphical elements in academic or informational texts

    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
    forman
    -0.07
    lett
    -0.07
     lou
    -0.06
     पड
    -0.06
    _utf
    -0.06
    á»ijng
    -0.06
     Leather
    -0.06
     containment
    -0.06
    èŃ
    -0.06
    bower
    -0.06
    POSITIVE LOGITS
     throughout
    0.08
    oids
    0.08
    ikes
    0.07
    ipes
    0.07
     wherever
    0.06
    ĺ
    0.06
    ikel
    0.06
    stagram
    0.06
    resas
    0.06
    illo
    0.06
    Activations Density 0.008%

    No Known Activations