© 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. 3774
    Prev
    Next
    INDEX
    Explanations

    locations and contexts related to various topics

    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
    SharedPointer
    -0.08
    æ½
    -0.07
    vala
    -0.07
    æĨ
    -0.07
     eskort
    -0.07
    Ùĥت
    -0.07
    CLU
    -0.07
    огод
    -0.07
    iddi
    -0.07
    _LOOK
    -0.07
    POSITIVE LOGITS
     world
    0.07
     inside
    0.07
    isté
    0.06
     happening
    0.06
     lives
    0.06
    lesc
    0.06
    \Migrations
    0.06
    603
    0.06
    918
    0.06
    appen
    0.06
    Activations Density 0.030%

    No Known Activations