© 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. 17-LLAMASCOPE-RES-131K
    11. 28840
    Prev
    Next
    INDEX
    Explanations

    relationships and dependencies in complex arguments or conditions

    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
    rou
    -0.06
    azi
    -0.06
    ,
    -0.06
    ew
    -0.05
    ailand
    -0.05
     Ill
    -0.05
     Dil
    -0.05
    elo
    -0.05
     being
    -0.05
     aside
    -0.05
    POSITIVE LOGITS
    *)((
    0.08
    SION
    0.08
    缮ãĤĴ
    0.08
    ủa
    0.08
    вано
    0.07
    .bpm
    0.07
    اصÙĦÙĩ
    0.07
    dit
    0.07
    cak
    0.07
    ména
    0.07
    Activations Density 0.074%

    No Known Activations