© 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. 15-LLAMASCOPE-RES-131K
    11. 668
    Prev
    Next
    INDEX
    Explanations

    descriptions of past events and experiences in a narrative context

    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
    .ManyToMany
    -0.08
     tonight
    -0.07
     mastur
    -0.07
    ÙĤب
    -0.07
     éĢ
    -0.07
    tpl
    -0.07
    ä¿Ŀ
    -0.07
    ëĤĺ무
    -0.06
     tomorrow
    -0.06
    .myapplication
    -0.06
    POSITIVE LOGITS
    mare
    0.07
     critic
    0.06
     ëĭ¹ìĭľ
    0.06
    ctic
    0.06
    ride
    0.06
    oped
    0.06
     Telefon
    0.06
     Toastr
    0.06
     pride
    0.06
    ripe
    0.06
    Activations Density 0.009%

    No Known Activations