INDEX

Explanations

repeated use of the verb "are" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ossal

-0.16

ä¸Ģä¸ªäºº

-0.14

 RANGE

-0.14

Ø§ÙĩØ§

-0.13

 accompanied

-0.13

 Ð¾Ð¿ÑĢÐµÐ´ÐµÐ»ÐµÐ½

-0.13

mc

-0.13

 nghiÃªm

-0.13

EMBER

-0.13

orge

-0.13

POSITIVE LOGITS

 flock

0.27

vo

0.21

 unanimous

0.21

 waking

0.20

 clam

0.20

 beginning

0.20

 lining

0.20

 divided

0.20

 united

0.19

 quick

0.18

Activations Density 0.137%

repeated use of the verb "are" and its variations in various contexts

No Comments

No Known Activations