INDEX

Explanations

words and phrases that describe conditions or states related to evaluation or assessment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ilst

-0.17

beck

-0.17

portlet

-0.16

ãģģ

-0.16

istrovstvÃŃ

-0.15

actionDate

-0.15

_LSB

-0.15

_DEPRECATED

-0.15

Î·ÏĥÎ·

-0.15

mans

-0.14

POSITIVE LOGITS

ASIC

0.15

lich

0.14

cent

0.14

pedia

0.14

 Veter

0.14

ASP

0.14

0.13

_exclude

0.13

px

0.13

numeric

0.13

Activations Density 0.086%

words and phrases that describe conditions or states related to evaluation or assessment

No Comments

No Known Activations