INDEX

Explanations

phrases related to providing or requesting directions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

semble

-0.17

 leaps

-0.17

ertz

-0.16

-0.15

 Patel

-0.14

fony

-0.14

onom

-0.14

 gaps

-0.13

Foundation

-0.13

Gui

-0.13

POSITIVE LOGITS

elez

0.19

tÄ±ÄŁ

0.15

erule

0.15

0.14

iture

0.14

.badlogic

0.14

Ä±lÄ±m

0.14

ilst

0.14

aal

0.14

ÅĻej

0.14

Activations Density 0.003%

phrases related to providing or requesting directions

No Comments

No Known Activations

phrases related to providing or requesting directions

No Comments

No Known Activations