INDEX

Explanations

references and citations in texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

xac

-0.15

å¹¹

-0.14

illard

-0.14

stanov

-0.14

dit

-0.14

 DAMAGES

-0.13

ãĤĪãģĨ

-0.13

mq

-0.13

OrFail

-0.13

thro

-0.13

POSITIVE LOGITS

 references

0.35

references

0.35

 References

0.33

References

0.32

 REFERENCES

0.31

 foot

0.29

 Foot

0.28

 Bibli

0.28

 Sources

0.27

 bibliography

0.26

Activations Density 0.104%

references and citations in texts

No Comments

No Known Activations