© 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. 87635
    Prev
    Next
    INDEX
    Explanations

    descriptions of unique architectural features or structures

    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
     Becker
    -0.07
    embers
    -0.06
     McGregor
    -0.06
     Dixon
    -0.06
    acs
    -0.06
    .binding
    -0.06
    .AI
    -0.06
    ourn
    -0.06
     Mine
    -0.06
    lug
    -0.06
    POSITIVE LOGITS
     suspended
    0.07
    ella
    0.07
     suspend
    0.06
    assen
    0.06
     Floating
    0.06
    suspend
    0.06
    ña
    0.06
    اÙģÛĮ
    0.06
    èİİ
    0.06
    asan
    0.06
    Activations Density 0.007%

    No Known Activations