© 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. 74849
    Prev
    Next
    INDEX
    Explanations

    references to Islamic historical figures and events

    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
    cio
    -0.07
    antine
    -0.07
    abad
    -0.07
    dyn
    -0.07
    uto
    -0.07
    emade
    -0.07
    alars
    -0.07
    ajaran
    -0.06
    dependence
    -0.06
    mys
    -0.06
    POSITIVE LOGITS
    hled
    0.08
    iÅŁ
    0.07
     Locker
    0.07
    ãĥ³ãĥ
    0.06
     Tall
    0.06
    κηÏĤ
    0.06
    _LP
    0.06
     Funk
    0.06
     Kanunu
    0.06
    obraz
    0.06
    Activations Density 0.066%

    No Known Activations