© 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. 15-LLAMASCOPE-RES-131K
    11. 89063
    Prev
    Next
    INDEX
    Explanations

    references to mobile and computer devices

    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
    áº
    -0.07
     Independ
    -0.06
    atable
    -0.06
     accident
    -0.06
    $MESS
    -0.06
    zie
    -0.06
    atest
    -0.06
    ovit
    -0.06
    avir
    -0.06
     clo
    -0.06
    POSITIVE LOGITS
    Mob
    0.07
     Äijâu
    0.07
    nex
    0.07
    /mobile
    0.06
    mob
    0.06
     Mob
    0.06
    dac
    0.06
    Animate
    0.06
     mob
    0.06
    -mobile
    0.06
    Activations Density 0.020%

    No Known Activations