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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 105908
    Prev
    Next
    INDEX
    Explanations

    elements related to biographical and historical records

    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
     Retrieved
    -0.06
    ess
    -0.06
     =
    -0.06
    comm
    -0.06
    ahu
    -0.06
    iste
    -0.05
     Dev
    -0.05
     pres
    -0.05
     Comm
    -0.05
     case
    -0.05
    POSITIVE LOGITS
    IFO
    0.09
    uisse
    0.08
    Creator
    0.08
    eneg
    0.08
    edBy
    0.07
    "@
    0.07
    .struts
    0.07
    åĸĶ
    0.07
     HEAP
    0.07
    emark
    0.07
    Activations Density 0.011%

    No Known Activations