INDEX

Explanations

phrases indicating intent or purpose

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

itchen

-0.15

rech

-0.15

fa

-0.15

usercontent

-0.15

 brand

-0.14

iece

-0.14

ÑĢÐµÐº

-0.14

 recom

-0.14

essler

-0.14

á»¯u

-0.14

POSITIVE LOGITS

 meant

0.18

warf

0.16

for

0.16

ioned

0.15

_INITIALIZER

0.15

/request

0.15

é¼

0.15

IONS

0.14

iyi

0.14

Activations Density 0.017%

phrases indicating intent or purpose

No Comments

No Known Activations