INDEX

Explanations

highly frequently used auxiliary and modal verbs alongside major ideas or claims in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Äįi

-0.19

zÅĳ

-0.16

ermen

-0.16

stdcall

-0.15

iferay

-0.15

startIndex

-0.15

ÅĻeb

-0.15

ç´Ģ

-0.15

AlgorithmException

-0.15

 gast

-0.14

POSITIVE LOGITS

RV

0.16

 Brig

0.15

 Beast

0.15

Ĭ

0.14

åŀĤ

0.14

ANTA

0.13

opp

0.13

 Kemp

0.13

(inplace

0.13

 Creed

0.13

Activations Density 0.002%

highly frequently used auxiliary and modal verbs alongside major ideas or claims in the text

No Comments

No Known Activations