© 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. 87931
    Prev
    Next
    INDEX
    Explanations

    expressions of connection and emotional insight

    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
    ooter
    -0.07
    roe
    -0.06
    ucci
    -0.06
    ouver
    -0.06
    Capability
    -0.06
    ãĤ¢ãĥ¼
    -0.06
     fun
    -0.06
    aten
    -0.06
     Morrow
    -0.06
     Ark
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    ilha
    0.07
     Amen
    0.07
     Applies
    0.07
    Ø´ÙĨ
    0.07
    obox
    0.07
    amen
    0.07
    รà¸ĩ
    0.07
    agara
    0.06
    OffsetTable
    0.06
    Activations Density 0.008%

    No Known Activations