© 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. 74514
    Prev
    Next
    INDEX
    Explanations

    references to specific document types, headings, or categories

    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
    ryption
    -0.07
    antt
    -0.07
    ofday
    -0.07
     Äiji
    -0.07
    ška
    -0.07
    Prostit
    -0.07
    à¥įरब
    -0.06
    à¥įरथ
    -0.06
     \"
    -0.06
    .setter
    -0.06
    POSITIVE LOGITS
     AssemblyCopyright
    0.07
     Certif
    0.06
    nock
    0.06
    odore
    0.06
    alia
    0.06
    çĵ
    0.06
     ÎĶε
    0.06
    etheless
    0.06
    lea
    0.06
    ILT
    0.06
    Activations Density 0.599%

    No Known Activations