© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 60594
    Prev
    Next
    INDEX
    Explanations

    instances of the word "first" and its related contexts

    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
    erais
    -0.06
    tains
    -0.06
    .library
    -0.06
    ivot
    -0.06
    ÅĽmy
    -0.06
     baÅŁÄ±na
    -0.06
    gos
    -0.06
    OPY
    -0.06
    ibel
    -0.06
    è¨ĪåĬĥ
    -0.06
    POSITIVE LOGITS
     post
    0.09
    =post
    0.07
    óst
    0.07
    ạm
    0.07
    post
    0.07
     full
    0.07
    -ever
    0.07
    iger
    0.07
     ever
    0.07
     Flesh
    0.07
    Activations Density 0.025%

    No Known Activations