Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 118714
    Prev
    Next
    INDEX
    Explanations

    phrases related to citations or references to external sources

    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
    ume
    -0.06
     ac
    -0.06
     acc
    -0.06
    aire
    -0.06
    (.
    -0.06
    ause
    -0.06
    â̦
    -0.06
    wyn
    -0.06
    andler
    -0.06
     (.
    -0.06
    POSITIVE LOGITS
     èĩªåĬ¨çĶŁæĪIJ
    0.07
    ffen
    0.07
    Č↵
    0.07
    osti
    0.07
    igsaw
    0.07
    ä¸Ŀ
    0.07
    UNKNOWN
    0.07
    itu
    0.07
     "-";↵
    0.07
     Hath
    0.07
    Activations Density 0.001%

    No Known Activations