© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75348
    Prev
    Next
    INDEX
    Explanations

    instances of content updates or changes in publication status

    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
    ово
    -0.07
    ente
    -0.06
    erties
    -0.06
    icl
    -0.06
    atin
    -0.06
     todd
    -0.06
     retr
    -0.06
    ãĥ©ãĤ¹
    -0.06
     Bord
    -0.06
    ysz
    -0.06
    POSITIVE LOGITS
    stream
    0.06
    ¦
    0.06
     Polo
    0.06
    ves
    0.06
    anoi
    0.06
    paired
    0.06
    ζÏĮ
    0.06
     cha
    0.06
    wiÄħ
    0.06
    cakes
    0.05
    Activations Density 0.002%

    No Known Activations