© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118614
    Prev
    Next
    INDEX
    Explanations

    references to personal observations and social gatherings

    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
     finish
    -0.07
    insk
    -0.07
    ãģĶ
    -0.06
    çķ°
    -0.06
     Annual
    -0.06
    cock
    -0.06
     annual
    -0.06
    emey
    -0.06
    bling
    -0.06
    -webpack
    -0.06
    POSITIVE LOGITS
    >\<^
    0.07
     daily
    0.07
     nightly
    0.07
     Ulus
    0.07
    Indented
    0.07
    turnstile
    0.06
    Ĩ
    0.06
    åĩºåĶ®
    0.06
    daily
    0.06
    //--------------------------------------------------------------↵
    0.06
    Activations Density 0.002%

    No Known Activations