© 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. 61748
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal and organizational frameworks

    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
    psc
    -0.07
    aab
    -0.07
    mae
    -0.07
    inem
    -0.07
    ovice
    -0.06
    ervised
    -0.06
     Velvet
    -0.06
    lesc
    -0.06
    Leaks
    -0.06
     suction
    -0.05
    POSITIVE LOGITS
    обÑĢаз
    0.08
    leader
    0.07
    گذ
    0.07
    SWG
    0.07
    /framework
    0.07
     Zac
    0.07
    éĸĢ
    0.07
    OffsetTable
    0.07
    æŁı
    0.07
    pmat
    0.07
    Activations Density 0.014%

    No Known Activations