© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127134
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting the invitation to contact or communicate

    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
    aris
    -0.07
    chs
    -0.07
    ertools
    -0.06
    ptal
    -0.06
     plein
    -0.06
    pent
    -0.06
    à¸ĵ
    -0.06
    _ROM
    -0.06
    rimon
    -0.06
    .integration
    -0.06
    POSITIVE LOGITS
    çµ
    0.07
    ((__
    0.07
    alls
    0.07
     Fay
    0.06
     Wesley
    0.06
    470
    0.06
     komm
    0.06
    صاÙĦ
    0.06
    inds
    0.06
    .loaded
    0.06
    Activations Density 0.001%

    No Known Activations