INDEX

Explanations

terms related to boundaries and interfaces between concepts or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

apl

-0.17

/*@

-0.17

poo

-0.16

entai

-0.15

 necessarily

-0.15

echa

-0.14

lek

-0.14

 correspond

-0.14

uw

-0.14

IZE

-0.14

POSITIVE LOGITS

ething

0.21

 between

0.20

 giá»¯a

0.17

.updateDynamic

0.17

 Between

0.17

voke

0.15

 Ð¼ÐµÐ¶Ð´Ñĥ

0.15

variant

0.15

between

0.15

Ð°Ð½Ð¸ÑĨ

0.15

Activations Density 0.208%

terms related to boundaries and interfaces between concepts or categories

No Comments

No Known Activations