INDEX

Explanations

entities associated with corporate and organizational names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

BOSE

-0.18

 -*-č↵

-0.16

 sÃ¸ger

-0.16

Ø²Ùħ

-0.14

ëĭ¥

-0.14

pcl

-0.14

Ð½ÐµÑĤ

-0.14

-INF

-0.14

SV

-0.13

ICollection

-0.13

POSITIVE LOGITS

reso

0.15

 truncate

0.15

uries

0.14

dent

0.14

.globalData

0.14

ww

0.14

hap

0.14

 Ability

0.13

als

0.13

pga

0.13

Activations Density 0.087%

entities associated with corporate and organizational names

No Comments

No Known Activations