© 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. 5-LLAMASCOPE-RES-131K
    11. 126507
    Prev
    Next
    INDEX
    Explanations

    phrases related to making tasks simpler or more accessible

    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
    cho
    -0.07
    جÙħ
    -0.07
    elsing
    -0.06
    ÐĴС
    -0.06
    serve
    -0.06
    Touches
    -0.06
    بار
    -0.06
    umu
    -0.06
    :frame
    -0.06
    edImage
    -0.06
    POSITIVE LOGITS
    -than
    0.08
     "(\<
    0.07
    ipers
    0.07
    arnings
    0.06
    eps
    0.06
    ncia
    0.06
    ions
    0.06
     Kem
    0.06
     Pend
    0.06
     =============================================================================↵
    0.05
    Activations Density 0.007%

    No Known Activations