INDEX

Explanations

terms related to geographical and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

tion

-0.14

antal

-0.14

uble

-0.14

 kino

-0.14

idences

-0.13

anker

-0.13

 Leban

-0.12

æľĽ

-0.12

.ak

-0.12

.UIManager

-0.12

POSITIVE LOGITS

ãĤº

0.14

à¤¾à¤²à¤ķ

0.14

¯

0.14

 ########.

0.14

alling

0.14

 Tarif

0.14

ÑĦÐ¾ÑĢÐ¼Ð¸

0.14

icie

0.13

bes

0.13

LLU

0.13

Activations Density 0.009%

terms related to geographical and numerical data

No Comments

No Known Activations