© 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. 15-LLAMASCOPE-RES-131K
    11. 1076
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and"

    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
    ackers
    -0.08
    typeid
    -0.06
     DJ
    -0.06
    ãĤ¯ãĤ»
    -0.06
     sacr
    -0.06
    &gt
    -0.06
     &#
    -0.06
    Ø®ÙĪاÙĨ
    -0.06
    िध
    -0.06
    ìĹĶ
    -0.06
    POSITIVE LOGITS
    è³ŀ
    0.07
    iaux
    0.07
    gress
    0.06
    \-
    0.06
    robe
    0.06
    ẩn
    0.06
    42
    0.06
    eczy
    0.06
    hall
    0.06
    uyo
    0.06
    Activations Density 0.000%

    No Known Activations