INDEX

Explanations

terms related to financial instruments and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ington

-0.17

inja

-0.16

inati

-0.15

hic

-0.15

ye

-0.15

inion

-0.14

wert

-0.14

ãĢħ

-0.14

-eyed

-0.14

upy

-0.14

POSITIVE LOGITS

edImage

0.20

ary

0.19

agna

0.16

oen

0.16

aries

0.16

ment

0.16

acle

0.16

maal

0.16

ing

0.15

/disable

0.15

Activations Density 0.036%

terms related to financial instruments and documentation

No Comments

No Known Activations