© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 117989
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and information processing

    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
    hausen
    -0.07
    ufe
    -0.07
    stalk
    -0.07
    pte
    -0.07
    oret
    -0.07
    emo
    -0.06
    isted
    -0.06
    à¸ĩ
    -0.06
    totalCount
    -0.06
     Gilbert
    -0.06
    POSITIVE LOGITS
     should
    0.08
    á»ijc
    0.07
     Expect
    0.06
    ìŀĦ
    0.06
     expected
    0.06
     hãy
    0.06
    should
    0.06
    Should
    0.06
     Should
    0.06
    iffer
    0.06
    Activations Density 0.033%

    No Known Activations