© 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 EvalsExportsinterp-engineNEWAPI 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. 120673
    Prev
    Next
    INDEX
    Explanations

    references to environmental change and loss

    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
    arget
    -0.07
    èĽĽ
    -0.07
    nton
    -0.06
     aku
    -0.06
     Ùħخت
    -0.06
    nest
    -0.06
    pps
    -0.06
    گار
    -0.06
    ichel
    -0.06
    roke
    -0.06
    POSITIVE LOGITS
     shrink
    0.07
     Portions
    0.07
     portions
    0.07
     now
    0.06
     retreat
    0.06
    shr
    0.06
    ümÃ¼ÅŁ
    0.06
     Retreat
    0.06
     land
    0.06
     Clearance
    0.06
    Activations Density 0.016%

    No Known Activations