© 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. 29664
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to network performance and management

    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
    enco
    -0.07
     δÏħνα
    -0.07
    osa
    -0.07
    imps
    -0.07
    EFA
    -0.07
    iyel
    -0.06
    EEP
    -0.06
    imity
    -0.06
    áš
    -0.06
    ISTA
    -0.06
    POSITIVE LOGITS
    okia
    0.07
    öh
    0.06
     unreliable
    0.06
    itone
    0.06
     performance
    0.06
     åĿ
    0.06
    iko
    0.06
     Guaranteed
    0.06
     redo
    0.06
    .lat
    0.06
    Activations Density 0.029%

    No Known Activations