INDEX

Explanations

terms related to combating negative effects or risks to health and the environment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

haled

-0.17

oser

-0.17

elves

-0.16

fÃ¼h

-0.16

ehler

-0.16

ollar

-0.15

LEAR

-0.15

ulings

-0.14

 aÃ§Ä±

-0.14

uras

-0.14

POSITIVE LOGITS

ewear

0.15

Jvm

0.15

ong

0.14

ÙħØ³

0.14

ysi

0.14

catch

0.14

çĥĪ

0.13

 Acquisition

0.13

 nháº¥n

0.13

Activations Density 0.648%

terms related to combating negative effects or risks to health and the environment

No Comments

No Known Activations