© 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. 129131
    Prev
    Next
    INDEX
    Explanations

    variations of the root word 'add' or related phonetic patterns

    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
    rál
    -0.07
     customary
    -0.06
    osoph
    -0.06
    issen
    -0.06
     Hue
    -0.06
     Boss
    -0.05
    alter
    -0.05
    ray
    -0.05
    imei
    -0.05
    aura
    -0.05
    POSITIVE LOGITS
    sez
    0.07
    imoto
    0.07
    ooled
    0.07
    -window
    0.07
    Ĺi
    0.07
    ashire
    0.07
    .getElements
    0.07
    رÙĪب
    0.06
    ipl
    0.06
    aÄŁa
    0.06
    Activations Density 0.038%

    No Known Activations