© 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. 55730
    Prev
    Next
    INDEX
    Explanations

    occurrences of quotation marks or references to dialogue

    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
    irm
    -0.07
    arel
    -0.06
    kee
    -0.06
    uml
    -0.06
    strength
    -0.06
    Uvs
    -0.06
    pcb
    -0.06
     fame
    -0.06
    eries
    -0.06
    iasi
    -0.06
    POSITIVE LOGITS
    usch
    0.06
    ">//
    0.06
    ARCH
    0.06
     Mile
    0.06
    302
    0.06
    _unpack
    0.06
    @dynamic
    0.06
    оÑİ
    0.06
    (disposing
    0.06
    geme
    0.06
    Activations Density 0.000%

    No Known Activations