© 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. 119403
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships and properties within network structures

    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
    interrupt
    -0.06
    EXP
    -0.06
     taj
    -0.06
    èı²
    -0.06
    _EXP
    -0.06
     smo
    -0.06
    owi
    -0.06
     pitch
    -0.06
    uk
    -0.06
    (íģ¬ê¸°
    -0.06
    POSITIVE LOGITS
    ixels
    0.07
    issy
    0.06
    rawn
    0.06
    inen
    0.06
     Schro
    0.06
    daÅŁ
    0.06
     Dude
    0.06
    ynes
    0.06
    valuator
    0.06
     legitimately
    0.06
    Activations Density 0.035%

    No Known Activations