© 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. 4146
    Prev
    Next
    INDEX
    Explanations

    themes related to conflict and opposition

    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
    lias
    -0.07
    ole
    -0.07
    _timing
    -0.07
    ense
    -0.07
    ilio
    -0.06
    .Tween
    -0.06
     üzerinden
    -0.06
    _ISS
    -0.06
    ENSE
    -0.06
    à¹Ģ
    -0.06
    POSITIVE LOGITS
    yne
    0.06
    Cog
    0.06
     peace
    0.06
     actively
    0.06
    setVisible
    0.06
     cocci
    0.06
    OrderId
    0.05
    ãĥĥãĤ«ãĥ¼
    0.05
    vos
    0.05
     purs
    0.05
    Activations Density 0.024%

    No Known Activations