© 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. 105046
    Prev
    Next
    INDEX
    Explanations

    instances of "is" indicating state or existence

    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
    arness
    -0.07
    vak
    -0.07
    urm
    -0.06
    uros
    -0.06
    izzare
    -0.06
    ektiv
    -0.06
    ABCDEFGHIJKLMNOP
    -0.06
    phan
    -0.06
    clamation
    -0.06
    uchen
    -0.06
    POSITIVE LOGITS
    BUF
    0.07
    alone
    0.07
    ê¶Į
    0.06
     sharedInstance
    0.06
    æĮĩ导
    0.06
    çŃ
    0.06
    edImage
    0.06
     kit
    0.06
     Ùħشتر
    0.06
    spr
    0.06
    Activations Density 0.000%

    No Known Activations