© 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. 40141
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty and statements related to claims and accusations

    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
    alloca
    -0.06
    gnu
    -0.06
    shouldBe
    -0.06
    ÑģеÑĢ
    -0.06
     undone
    -0.06
    нез
    -0.06
     Enough
    -0.06
    linger
    -0.06
    itten
    -0.06
    Ñı
    -0.06
    POSITIVE LOGITS
     neither
    0.18
     not
    0.17
     nicht
    0.15
     no
    0.14
     không
    0.14
     tidak
    0.14
     नह
    0.14
     nowhere
    0.14
     не
    0.14
     niet
    0.14
    Activations Density 0.238%

    No Known Activations