INDEX

Explanations

phrases related to events and activities taking place

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 acceler

-0.17

 Franken

-0.16

oppins

-0.16

culate

-0.15

 Tradable

-0.15

endency

-0.15

.figure

-0.14

ÑĢÐ°ÑģÑĤÐ°

-0.14

prec

-0.14

ä¹ħ

-0.13

POSITIVE LOGITS

ition

0.15

Voy

0.15

 Shawn

0.14

_SHARED

0.14

emaker

0.14

 process

0.14

oco

0.14

mp

0.13

tin

0.13

Activations Density 0.140%

phrases related to events and activities taking place

No Comments

No Known Activations