Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84328
    Prev
    Next
    INDEX
    Explanations

    the phrase "on the other hand"

    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
    inand
    -0.07
     indeed
    -0.07
     daher
    -0.07
    voj
    -0.07
    ÑĤÑİ
    -0.07
    zes
    -0.07
     Mim
    -0.06
     böylece
    -0.06
    нев
    -0.06
    ouncy
    -0.06
    POSITIVE LOGITS
    innen
    0.08
     side
    0.08
     Side
    0.08
    wil
    0.07
    że
    0.07
    Side
    0.06
    thr
    0.06
    icap
    0.06
    -side
    0.06
    ,
    0.06
    Activations Density 0.006%

    No Known Activations