© 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. 94137
    Prev
    Next
    INDEX
    Explanations

    words related to the act of initiating or starting something

    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
    ÄĻp
    -0.08
    ÑĶм
    -0.08
    ël
    -0.07
    .MixedReality
    -0.07
    FEATURE
    -0.07
    æľŃ
    -0.07
    avaÅŁ
    -0.07
    /Instruction
    -0.07
    .EVT
    -0.07
     kancel
    -0.07
    POSITIVE LOGITS
     attacks
    0.08
     attack
    0.07
     launched
    0.07
     probe
    0.07
     launch
    0.07
     careers
    0.07
     into
    0.07
     campaign
    0.06
     campaigns
    0.06
    /res
    0.06
    Activations Density 0.017%

    No Known Activations