© 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. 1741
    Prev
    Next
    INDEX
    Explanations

    phrases related to perceptions and classifications of entities or events

    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
     things
    -0.07
    çĶŁçļĦ
    -0.06
    things
    -0.06
    arken
    -0.06
     Domin
    -0.06
    iant
    -0.06
    çļĦåľ°æĸ¹
    -0.06
    hani
    -0.06
     Things
    -0.06
     thing
    -0.05
    POSITIVE LOGITS
     counterpart
    0.08
    raison
    0.08
    own
    0.08
    lef
    0.08
    adero
    0.08
    contents
    0.08
    OWN
    0.08
    wner
    0.08
     inhabitants
    0.08
    nature
    0.08
    Activations Density 0.094%

    No Known Activations