© 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. 16064
    Prev
    Next
    INDEX
    Explanations

    programming-related structures and syntax

    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
    .Reporting
    -0.08
    ενο
    -0.08
    Ø«
    -0.08
    ëĿ½
    -0.08
    rax
    -0.07
    cak
    -0.07
    Ä°n
    -0.07
    (It
    -0.07
    klady
    -0.07
    олн
    -0.07
    POSITIVE LOGITS
    asp
    0.06
     Pearce
    0.06
    enty
    0.06
    odore
    0.06
    419
    0.06
    ulin
    0.05
    iph
    0.05
    ustin
    0.05
    âĢ¦↵
    0.05
    ical
    0.05
    Activations Density 0.057%

    No Known Activations