INDEX

Explanations

references to legal judgments and court decisions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ilde

-0.16

è¢ĭ

-0.15

weeney

-0.15

azy

-0.15

chos

-0.14

.newBuilder

-0.14

uzzy

-0.14

 Lama

-0.14

elim

-0.14

ÑģÐ¸

-0.14

POSITIVE LOGITS

 Bench

0.24

 bench

0.24

bench

0.22

PIL

0.21

 hearing

0.19

disposed

0.19

 benches

0.18

direction

0.18

 advocate

0.18

 directions

0.18

Activations Density 0.060%

references to legal judgments and court decisions

No Known Activations