© 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. 8360
    Prev
    Next
    INDEX
    Explanations

    personal experiences and perspectives related to change and adaptation

    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
     themselves
    -0.40
     us
    -0.34
     itself
    -0.27
     yourselves
    -0.26
     ours
    -0.24
     nous
    -0.21
     nám
    -0.20
     we
    -0.19
     me
    -0.19
     μαÏĤ
    -0.18
    POSITIVE LOGITS
     myself
    0.85
     my
    0.43
     mijn
    0.40
    æĪijçļĦ
    0.40
     minha
    0.36
     meinem
    0.33
     jsem
    0.33
     бÑĥдÑĥ
    0.33
     meiner
    0.30
     meine
    0.30
    Activations Density 1.754%

    No Known Activations