© 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. 78526
    Prev
    Next
    INDEX
    Explanations

    instances of verbs related to evaluation and observation

    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
    imu
    -0.06
    anken
    -0.06
    edd
    -0.06
    örper
    -0.06
    IT
    -0.06
    ITT
    -0.06
    id
    -0.06
    ep
    -0.06
    afa
    -0.06
    ernen
    -0.05
    POSITIVE LOGITS
     them
    0.19
    å®ĥ
    0.18
     it
    0.17
    å®ĥ们
    0.17
     thereof
    0.17
     its
    0.16
     оно
    0.16
     nó
    0.16
    them
    0.14
     ниÑħ
    0.13
    Activations Density 0.003%

    No Known Activations