INDEX

Explanations

references to legal citations and case law

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

osa

-0.17

istrat

-0.16

ald

-0.16

adero

-0.15

shint

-0.15

.integration

-0.14

à¹Īà¸²à¸Ĺ

-0.14

OAD

-0.14

ropoda

-0.14

ÑģÐ°

-0.14

POSITIVE LOGITS

rics

0.16

Soc

0.15

quential

0.15

ensions

0.14

ileo

0.14

imary

0.14

arth

0.14

ocup

0.14

mith

0.13

_fwd

0.13

Activations Density 0.174%

references to legal citations and case law

No Known Activations