© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 89198
    Prev
    Next
    INDEX
    Explanations

    details about wildlife regulations and conservation efforts

    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
    ³
    -0.06
    probe
    -0.06
    heed
    -0.06
    éª
    -0.06
    reff
    -0.06
    stadt
    -0.06
    508
    -0.06
    stal
    -0.06
    swick
    -0.06
     grop
    -0.06
    POSITIVE LOGITS
     kill
    0.10
     kills
    0.09
     killing
    0.08
     killings
    0.08
     targets
    0.08
    kill
    0.08
     Kills
    0.07
    DDD
    0.07
    _targets
    0.07
     target
    0.07
    Activations Density 0.008%

    No Known Activations