INDEX

Explanations

negative or dismissive sentiments

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

Negative Logits

agnost

-0.16

 tends

-0.16

hear

-0.15

-0.14

 tend

-0.14

agma

-0.14

iscal

-0.14

æ´²

-0.14

agna

-0.14

IBE

-0.14

POSITIVE LOGITS

aida

0.16

íĥĿ

0.15

'gc

0.15

enus

0.14

 pall

0.14

etre

0.14

-icons

0.14

char

0.13

 Berm

0.13

Eid

0.13

Activations Density 0.099%

negative or dismissive sentiments

No Known Activations