© 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. 84754
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to documentation and oversight issues

    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
    'gc
    -0.08
    anchors
    -0.07
    (æľĪ
    -0.07
    (åľŁ
    -0.07
    lexport
    -0.07
     ÐľÐµÑģÑĤо
    -0.07
    UNUSED
    -0.07
    ÅĻez
    -0.07
    anchor
    -0.07
    ืà¹ī
    -0.07
    POSITIVE LOGITS
     result
    0.07
     consequence
    0.07
     consequences
    0.07
     exploited
    0.06
     resulting
    0.06
     results
    0.06
     causes
    0.06
     resulted
    0.06
     caused
    0.06
    aran
    0.06
    Activations Density 0.053%

    No Known Activations