© 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. 40576
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and liabilities

    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
     sami
    -0.06
    abez
    -0.06
    rese
    -0.06
    taire
    -0.06
     stakes
    -0.06
    assin
    -0.06
    )prepare
    -0.06
    æķµ
    -0.06
    çĶ³
    -0.06
    onden
    -0.06
    POSITIVE LOGITS
    wald
    0.07
     McCart
    0.06
    uyo
    0.06
    kili
    0.06
     ministries
    0.06
    ua
    0.06
    _drv
    0.06
    ugal
    0.06
    uy
    0.06
    @stop
    0.06
    Activations Density 0.002%

    No Known Activations