INDEX

Explanations

references to spatial contexts or locations within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ses

-0.19

anna

-0.15

chip

-0.15

Ã©ri

-0.14

iller

-0.14

yat

-0.14

alties

-0.14

aren

-0.14

Å¾iv

-0.14

ald

-0.14

POSITIVE LOGITS

most

0.16

 regard

0.16

lac

0.15

/out

0.15

ë¶Ģ

0.14

creasing

0.14

ÙħØ§Ø±

0.14

 spirit

0.14

 ÑģÐ¾Ð±Ð¾Ð¹

0.13

Activations Density 0.050%

references to spatial contexts or locations within a text

No Comments

No Known Activations