INDEX

Explanations

phrases related to harm or injury

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ancel

-0.15

anten

-0.14

Å¾en

-0.14

Ø±Ø¯

-0.14

ÅĤu

-0.13

cess

-0.13

Pix

-0.13

vaÅ¾

-0.13

 which

-0.13

ãĥĢãĤ¤

-0.13

POSITIVE LOGITS

 ÙĪØ§ÙĦØªÙĬ

0.17

ï¼īãģ®

0.16

:;↵

0.15

ï¼īçļĦ

0.15

@js

0.15

lew

0.15

 sino

0.15

ï¼Įä»¥åıĬ

0.15

])->

0.14

')['

0.14

Activations Density 1.257%

phrases related to harm or injury

No Comments

No Known Activations