© 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. 15-LLAMASCOPE-RES-131K
    6. 61786
    Prev
    Next
    INDEX
    Explanations

    programming functions and statements related to output and control flow in code

    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
    æŁĦ
    -0.06
    _UNUSED
    -0.06
    abant
    -0.06
    OST
    -0.06
     Granny
    -0.06
    _opt
    -0.06
    OutputStream
    -0.06
    apping
    -0.06
     Stem
    -0.06
    ettel
    -0.05
    POSITIVE LOGITS
    amber
    0.07
     赤
    0.07
    igor
    0.07
     âĸ³
    0.07
    -js
    0.07
    666
    0.06
    redo
    0.06
    éĽª
    0.06
    ongyang
    0.06
     rdr
    0.06
    Activations Density 0.002%

    No Known Activations