© 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. 107395
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs and expressions related to initiation or creation

    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
    еÑĢÑĤа
    -0.08
    ofilm
    -0.07
    ponge
    -0.07
    :normal
    -0.07
    zÃŃ
    -0.07
     Stable
    -0.07
    ovich
    -0.06
    ilitation
    -0.06
     serm
    -0.06
    suma
    -0.06
    POSITIVE LOGITS
     mark
    0.07
     headlines
    0.07
     ingress
    0.07
    liÄį
    0.07
     appearance
    0.07
     debut
    0.06
    lar
    0.06
     waves
    0.06
     jet
    0.06
     cameo
    0.06
    Activations Density 0.013%

    No Known Activations