© 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. 117021
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial impacts and estimates of damage following a disaster

    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
    olith
    -0.08
    OP
    -0.07
     Brend
    -0.07
    å£
    -0.07
    ữ
    -0.07
     heats
    -0.06
    aval
    -0.06
    리ìĸ´
    -0.06
    ัà¸Ķส
    -0.06
    ourcem
    -0.06
    POSITIVE LOGITS
     insurance
    0.09
     insured
    0.09
     losses
    0.08
     Insurance
    0.08
     cost
    0.07
     total
    0.07
     victim
    0.06
     loss
    0.06
     property
    0.06
    Insurance
    0.06
    Activations Density 0.004%

    No Known Activations