© 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. 93473
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming

    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
    erge
    -0.06
    ÐłÐĺ
    -0.06
    ÑģÑı
    -0.06
     cust
    -0.06
    oret
    -0.06
    mary
    -0.06
    SITE
    -0.06
     Genel
    -0.06
    rish
    -0.06
    oa
    -0.06
    POSITIVE LOGITS
    alk
    0.07
    -addons
    0.07
    UIApplication
    0.07
    eof
    0.07
    elong
    0.07
    abis
    0.07
     eof
    0.06
    átek
    0.06
    375
    0.06
    _rat
    0.06
    Activations Density 0.005%

    No Known Activations