© 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. 4-LLAMASCOPE-RES-32K
    11. 30037
    Prev
    Next
    INDEX
    Explanations

    references to circular shapes or formations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cabr
    -0.16
     Kaw
    -0.15
    esse
    -0.15
    uncated
    -0.14
    auge
    -0.14
    ãĥĥãĤ¯
    -0.14
    .Companion
    -0.14
    .AppendText
    -0.14
    ember
    -0.14
    ائ
    -0.13
    POSITIVE LOGITS
    åľĪ
    0.17
    athe
    0.16
    à¸Ħรà¸ĩ
    0.15
    Äįan
    0.15
     circle
    0.15
     rim
    0.15
    å¥Ĺ
    0.15
    adan
    0.15
     knowledge
    0.14
    allas
    0.14
    Activations Density 0.260%

    No Known Activations