Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96181
    Prev
    Next
    INDEX
    Explanations

    key terms related to governance and national news

    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
    enstein
    -0.07
    ipar
    -0.07
    fahren
    -0.07
    aset
    -0.07
    lical
    -0.07
    gili
    -0.07
    ebek
    -0.07
    aseline
    -0.07
    reau
    -0.07
    enheim
    -0.07
    POSITIVE LOGITS
     Zimmerman
    0.06
    ylie
    0.06
     artery
    0.05
     Whit
    0.05
     reservations
    0.05
    ì¡°
    0.05
    vs
    0.05
     Tr
    0.05
    stand
    0.05
    cloud
    0.05
    Activations Density 0.057%

    No Known Activations