© 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. 74922
    Prev
    Next
    INDEX
    Explanations

    phrases related to accountability and control

    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
    uem
    -0.08
     Dân
    -0.07
    ¦Ĥ
    -0.07
    snake
    -0.07
    LayoutManager
    -0.07
    (=)
    -0.07
    otu
    -0.07
    zeich
    -0.07
    λÏī
    -0.07
    undi
    -0.07
    POSITIVE LOGITS
    /of
    0.06
     fault
    0.06
     involved
    0.06
     Boh
    0.05
     Minor
    0.05
     usual
    0.05
    ign
    0.05
    antro
    0.05
    .sin
    0.05
    ุ
    0.05
    Activations Density 0.003%

    No Known Activations