INDEX

Explanations

elements related to legal terminology and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

zel

-0.19

nee

-0.16

Gam

-0.15

agna

-0.14

 Cabr

-0.14

agli

-0.14

ycz

-0.14

ac

-0.14

ugh

-0.14

wend

-0.13

POSITIVE LOGITS

eh

0.16

hci

0.14

Sad

0.14

Ð¾ÑĢÐ¸

0.14

antas

0.14

Ð¾ÑĢÑĸ

0.13

arker

0.13

idor

0.13

Activations Density 0.900%

elements related to legal terminology and references

No Comments

No Known Activations