© 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. 86223
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the current status or prevalence of concepts and practices

    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
    ekil
    -0.07
    ettle
    -0.07
    jian
    -0.06
    ixin
    -0.06
    μί
    -0.06
    rieve
    -0.06
    arton
    -0.06
    .fs
    -0.05
    rescia
    -0.05
    деÑĢ
    -0.05
    POSITIVE LOGITS
    опиÑģ
    0.08
     increasingly
    0.08
    íĭ°
    0.07
    è¶Ĭ
    0.07
    Become
    0.07
    ruz
    0.07
     modne
    0.07
     Vote
    0.06
    ibo
    0.06
    Ģ
    0.06
    Activations Density 0.045%

    No Known Activations