© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119398
    Prev
    Next
    INDEX
    Explanations

    elements related to templates and backend scripting in code

    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
    raphics
    -0.07
    idge
    -0.07
    ovÃŃ
    -0.07
     backlight
    -0.07
    GRAM
    -0.07
    ottle
    -0.06
    lass
    -0.06
     داÙħ
    -0.06
    даеÑĤ
    -0.06
     ((((
    -0.06
    POSITIVE LOGITS
    .tpl
    0.08
    tpl
    0.07
     links
    0.07
    :not
    0.07
     single
    0.06
    ocard
    0.06
    ancock
    0.06
    ucle
    0.06
    single
    0.06
    sil
    0.06
    Activations Density 0.016%

    No Known Activations