© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95752
    Prev
    Next
    INDEX
    Explanations

    technical specifications and components related to batteries and electronic systems

    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
    ,
    -0.09
    ↵
    -0.08
     and
    -0.07
    :
    -0.07
    ?
    -0.07
     briefly
    -0.07
    !
    -0.07
     |
    -0.06
     C
    -0.06
    amp
    -0.06
    POSITIVE LOGITS
    enticate
    0.09
    .struts
    0.08
    .opensource
    0.08
    formace
    0.08
     RuntimeObject
    0.08
    hexdigest
    0.08
    \Persistence
    0.08
    'gc
    0.08
    .xtext
    0.08
    "struct
    0.08
    Activations Density 0.014%

    No Known Activations