INDEX

Explanations

references to specific data or numerical values in 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 @ 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

vas

-0.15

unk

-0.15

antas

-0.15

UNK

-0.15

Ð½Ð¾Ð¾Ð±ÑĢÐ°Ð·

-0.14

bserv

-0.14

.staff

-0.14

à¸§à¸Ļ

-0.13

 Hindered

-0.13

 cancell

-0.13

POSITIVE LOGITS

ëī´

0.16

Ã¢n

0.15

bsd

0.14

 Playoff

0.14

aterangepicker

0.14

 boot

0.13

cy

0.13

cy

0.13

Won

0.13

.setCharacter

0.13

Activations Density 0.073%

references to specific data or numerical values in a text

No Comments

No Known Activations