© 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. 3754
    Prev
    Next
    INDEX
    Explanations

    calls to action or invitations to view or participate in something

    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
    dden
    -0.08
    avax
    -0.07
    AndView
    -0.07
    ieval
    -0.07
    adora
    -0.07
    enment
    -0.07
    soever
    -0.07
    strand
    -0.07
    одо
    -0.07
    TEGER
    -0.07
    POSITIVE LOGITS
     look
    0.07
     read
    0.07
     suppose
    0.06
     sol
    0.06
    yal
    0.06
     ald
    0.06
    -read
    0.06
     extension
    0.05
     see
    0.05
     example
    0.05
    Activations Density 0.009%

    No Known Activations