© 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. 61308
    Prev
    Next
    INDEX
    Explanations

    phrases related to theoretical concepts and conditions

    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
    avir
    -0.08
    fried
    -0.08
    quier
    -0.07
    inne
    -0.07
    DEX
    -0.07
    :maj
    -0.06
    .scalablytyped
    -0.06
    illet
    -0.06
    ocking
    -0.06
    UTERS
    -0.06
    POSITIVE LOGITS
     could
    0.17
    could
    0.15
     Could
    0.15
     theoretically
    0.14
    Could
    0.14
    oret
    0.14
     possibility
    0.12
     conce
    0.12
     potentially
    0.12
    çIJĨ论
    0.12
    Activations Density 0.091%

    No Known Activations