© 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. 83245
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate independence or separation from external influences or entities

    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
    cete
    -0.08
    cheid
    -0.08
    ruh
    -0.08
    elop
    -0.08
    _lcd
    -0.07
     nackte
    -0.07
    λιο
    -0.07
    ãİ
    -0.07
     åĥ
    -0.07
    ypy
    -0.07
    POSITIVE LOGITS
     other
    0.10
     others
    0.10
     any
    0.10
     separately
    0.07
     actual
    0.07
     yet
    0.07
     its
    0.07
     anymore
    0.07
     rest
    0.07
     anyone
    0.07
    Activations Density 0.014%

    No Known Activations