Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 60998
    Prev
    Next
    INDEX
    Explanations

    boolean expressions and control flow statements

    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
    ipay
    -0.07
    ersh
    -0.07
    .pretty
    -0.06
    xDB
    -0.06
     (_)
    -0.06
    ãĥ¼ãĤ¿ãĥ¼
    -0.06
    	wc
    -0.06
    xic
    -0.06
    AndPassword
    -0.05
    nst
    -0.05
    POSITIVE LOGITS
    ç¡
    0.07
    ãĥĸãĥŃ
    0.07
    in
    0.06
     autorelease
    0.06
    еÑĦ
    0.06
    aylight
    0.06
    ÑĢе
    0.06
    riter
    0.06
    éĤ¦
    0.06
    Markup
    0.06
    Activations Density 0.012%

    No Known Activations