© 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. 15-LLAMASCOPE-RES-131K
    11. 26947
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and code structure

    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
    виÑĩай
    -0.08
    cie
    -0.08
    окÑĢема
    -0.06
    ifen
    -0.06
    oire
    -0.06
     Phen
    -0.06
    ело
    -0.06
     Nes
    -0.06
     stripslashes
    -0.06
    ehr
    -0.06
    POSITIVE LOGITS
    utut
    0.08
    555
    0.07
    ÑģÑĤÑİ
    0.07
    ipse
    0.06
    PEND
    0.06
    aign
    0.06
    legate
    0.06
    indre
    0.06
    @nate
    0.06
     uncomment
    0.06
    Activations Density 0.076%

    No Known Activations