INDEX

Explanations

repeated phrases or constructions referring to "that" 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ãģĤãĤĭ

-0.17

icens

-0.16

ãģĬ

-0.16

ãģĤãģ£ãģŁ

-0.15

ãģĤãĤĬ

-0.15

slaught

-0.15

agnar

-0.15

oust

-0.14

.tell

-0.14

 yÃªn

-0.14

POSITIVE LOGITS

ching

0.21

oping

0.20

ched

0.20

are

0.17

upon

0.17

ch

0.17

soever

0.16

has

0.15

-Ð½Ð¸Ð±ÑĥÐ´ÑĮ

0.15

we

0.15

Activations Density 0.251%

repeated phrases or constructions referring to "that" in various contexts

No Comments

No Known Activations