© 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. 126408
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the quantity "two."

    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
    269
    -0.06
    avit
    -0.06
    elo
    -0.06
    Ñģи
    -0.06
    ADM
    -0.06
     Grip
    -0.06
    265
    -0.06
    leo
    -0.06
    egov
    -0.06
    ugins
    -0.06
    POSITIVE LOGITS
    ÙĪÙĤت
    0.07
    izabeth
    0.07
    InBackground
    0.07
    drop
    0.06
     Dut
    0.06
    dro
    0.06
    -sample
    0.06
    mium
    0.06
     Dro
    0.06
    جا
    0.06
    Activations Density 0.007%

    No Known Activations