© 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. 75683
    Prev
    Next
    INDEX
    Explanations

    expressions of love and appreciation for places and communities

    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
    ú
    -0.06
    633
    -0.06
    ocaust
    -0.06
     mastur
    -0.06
    .DOM
    -0.06
    eteria
    -0.06
    åºĨ
    -0.06
    iek
    -0.06
    aepernick
    -0.06
     £
    -0.06
    POSITIVE LOGITS
     audience
    0.07
     audiences
    0.07
    dera
    0.07
     hosp
    0.07
    hosts
    0.07
     Dagger
    0.07
    ç²ī
    0.07
    [Double
    0.06
    -cultural
    0.06
     memorable
    0.06
    Activations Density 0.017%

    No Known Activations