© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83908
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and development constructs

    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
    ault
    -0.07
    ´Ŀ
    -0.07
    iao
    -0.07
    amespace
    -0.07
    iddet
    -0.07
    .gameserver
    -0.07
    dana
    -0.07
     ordin
    -0.07
    CHANT
    -0.07
    .Reporting
    -0.07
    POSITIVE LOGITS
       
    0.07
    sted
    0.06
    lon
    0.06
     mod
    0.05
     Prev
    0.05
    kowski
    0.05
    boru
    0.05
    905
    0.05
    brids
    0.05
    ê¶Į
    0.05
    Activations Density 0.034%

    No Known Activations