INDEX

Explanations

legal terms and concepts related to agreements and indemnification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

acro

-0.14

 Lind

-0.14

agon

-0.14

 Moss

-0.14

TH

-0.14

 subt

-0.14

gear

-0.14

Hal

-0.13

ESH

-0.13

AIL

-0.13

POSITIVE LOGITS

rosso

0.16

osy

0.15

strand

0.15

zyst

0.15

 metav

0.15

axies

0.14

ftar

0.14

.ImageLayout

0.14

jni

0.14

paren

0.14

Activations Density 0.082%

legal terms and concepts related to agreements and indemnification

No Comments

No Known Activations