© 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. 24-LLAMASCOPE-RES-32K
    11. 4703
    Prev
    Next
    INDEX
    Explanations

    themes related to uncertainty and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     addCriterion
    -0.14
     αÏħÏĦά
    -0.14
    eyse
    -0.14
     nackte
    -0.14
     Erotik
    -0.14
    ục
    -0.13
    ebilir
    -0.13
    /Instruction
    -0.13
    oppers
    -0.12
    ãi
    -0.12
    POSITIVE LOGITS
     who
    1.13
    who
    0.96
     Who
    0.89
    Who
    0.84
     whom
    0.82
    è°ģ
    0.79
     quien
    0.73
     qui
    0.65
    誰
    0.64
     whose
    0.59
    Activations Density 0.266%

    No Known Activations