© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62527
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict or tension in narrative contexts

    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
     Pf
    -0.07
    ÑĤÑĮ
    -0.06
    ongo
    -0.06
    ãĥĩãĤ£ãĤ¢
    -0.06
    iddet
    -0.06
    _nf
    -0.06
    ouro
    -0.06
    anga
    -0.06
    opr
    -0.06
    iej
    -0.06
    POSITIVE LOGITS
    å¿ł
    0.07
    aaS
    0.07
    .Schema
    0.06
    quist
    0.06
    lic
    0.06
     unlike
    0.06
    åĬ±
    0.06
    ander
    0.06
    phin
    0.06
    aney
    0.06
    Activations Density 0.012%

    No Known Activations