© 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. 78152
    Prev
    Next
    INDEX
    Explanations

    formal terms related to corporate governance and compliance documentation

    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
    _mE
    -0.07
    ierz
    -0.07
    ording
    -0.07
     меÑĤалли
    -0.07
    itta
    -0.07
    _tA
    -0.07
    åĩ
    -0.07
    CanBe
    -0.07
    perm
    -0.07
    .pp
    -0.07
    POSITIVE LOGITS
     Undert
    0.07
    PEC
    0.06
     undertaking
    0.06
     sworn
    0.06
    agen
    0.05
    inters
    0.05
     Matrix
    0.05
     ren
    0.05
     hum
    0.05
     decl
    0.05
    Activations Density 0.003%

    No Known Activations