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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 60960
    Prev
    Next
    INDEX
    Explanations

    concepts related to conflict and resolution

    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
    tec
    -0.07
    dera
    -0.07
    æĭľ
    -0.07
    icha
    -0.07
    AGAIN
    -0.07
    anium
    -0.07
    éal
    -0.06
    edis
    -0.06
    inz
    -0.06
    asca
    -0.06
    POSITIVE LOGITS
     sometimes
    0.08
     Sometimes
    0.07
    sometimes
    0.07
     oneself
    0.07
    Sometimes
    0.07
    attern
    0.06
    ãĥ³ãĤº
    0.06
    amon
    0.06
    ruk
    0.06
    ometimes
    0.06
    Activations Density 0.065%

    No Known Activations