© 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. 87800
    Prev
    Next
    INDEX
    Explanations

    code structures or syntax elements in programming language snippets

    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
    idal
    -0.07
     Tec
    -0.06
     Dün
    -0.06
    ighted
    -0.06
    kker
    -0.06
    Ĩµ
    -0.06
    PEC
    -0.06
    è¾
    -0.06
    á»Ļc
    -0.06
    rit
    -0.06
    POSITIVE LOGITS
     case
    0.10
    edia
    0.09
     otherwise
    0.09
     else
    0.09
     esac
    0.09
     cases
    0.09
     Otherwise
    0.07
     Case
    0.07
     sonst
    0.07
    Case
    0.07
    Activations Density 0.031%

    No Known Activations