INDEX

Explanations

elements related to academic or artistic references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.17

StackNavigator

-0.16

ert

-0.16

bose

-0.15

oenix

-0.15

oker

-0.14

PERT

-0.14

ervo

-0.14

rypt

-0.13

asia

-0.13

POSITIVE LOGITS

 sources

0.19

##

0.17

 refs

0.17

 Sources

0.17

 Source

0.16

 source

0.16

References

0.16

 Kaynak

0.16

æĿ¥æºĲ

0.16

 references

0.16

Activations Density 0.048%

elements related to academic or artistic references

No Comments

No Known Activations