INDEX

Explanations

locations mentioned in relation to specific activities or entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ivan

-0.17

iable

-0.16

erie

-0.16

amos

-0.16

stoff

-0.15

ied

-0.15

anche

-0.15

ÐµÑģÐ¿

-0.14

ach

-0.14

 northern

-0.14

POSITIVE LOGITS

rogen

0.15

orro

0.15

à¤¯à¤°

0.14

dej

0.14

pine

0.14

ãĤ¦ãĥ³

0.14

 ÏħÏĢÎ¬ÏģÏĩÎ¿ÏħÎ½

0.13

oldown

0.13

Viewport

0.13

Activations Density 0.028%

locations mentioned in relation to specific activities or entities

No Comments

No Known Activations