© 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. 17-LLAMASCOPE-RES-131K
    6. 40265
    Prev
    Next
    INDEX
    Explanations

    references to informational pages or sections within a document

    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
    istrovstvÃŃ
    -0.07
    ysz
    -0.07
    etwork
    -0.07
    ys
    -0.07
    erie
    -0.06
     Fork
    -0.06
    lobal
    -0.06
    ysa
    -0.06
     terminals
    -0.06
     ìŀĪëĭ¤ê³ł
    -0.06
    POSITIVE LOGITS
    outu
    0.08
     page
    0.07
    ulp
    0.07
    547
    0.07
    abis
    0.06
    ÙĨدÙĬ
    0.06
    PDO
    0.06
    aÄį
    0.06
    unfold
    0.06
     section
    0.06
    Activations Density 0.008%

    No Known Activations