© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87223
    Prev
    Next
    INDEX
    Explanations

    terms associated with identifying and tracking pets

    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
    onda
    -0.07
    enegro
    -0.07
    imu
    -0.07
    nett
    -0.06
     UserController
    -0.06
     econom
    -0.06
    untu
    -0.06
    å´ĩ
    -0.06
    awns
    -0.06
    OKIE
    -0.06
    POSITIVE LOGITS
     implanted
    0.07
     chip
    0.06
     ID
    0.06
     humane
    0.06
     fees
    0.06
    ibe
    0.06
     pellets
    0.06
     DNA
    0.06
     identification
    0.06
    avax
    0.05
    Activations Density 0.002%

    No Known Activations