Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93833
    Prev
    Next
    INDEX
    Explanations

    mentions of methods for controlling or eradicating specific pest species

    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
     deducted
    -0.06
    TabPage
    -0.05
     stabil
    -0.05
    fel
    -0.05
    wald
    -0.05
     rings
    -0.05
    AllowAnonymous
    -0.05
     sign
    -0.05
     fel
    -0.05
     Raw
    -0.05
    POSITIVE LOGITS
     effectiveness
    0.09
     Kills
    0.08
     killing
    0.08
    ocide
    0.08
     kills
    0.08
    æĿĢ
    0.08
     lethal
    0.08
     kill
    0.08
     Killing
    0.08
     вÑģÑĤÑĥп
    0.08
    Activations Density 0.002%

    No Known Activations