INDEX

Explanations

phrases indicating conditions or qualifiers

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

iegel

-0.14

tua

-0.13

âĢĮØ¯

-0.13

 sice

-0.13

umper

-0.13

_intf

-0.13

 ÎķÏĢ

-0.13

 ÙĪÙĦÙĬ

-0.12

 Handy

-0.12

idan

-0.12

POSITIVE LOGITS

 otherwise

0.33

otherwise

0.28

 Otherwise

0.27

 OTHERWISE

0.25

Otherwise

0.23

-ÑĤÐ¾

0.18

 thereby

0.18

foy

0.17

Includes

0.17

 then

0.17

Activations Density 0.252%

phrases indicating conditions or qualifiers

No Comments

No Known Activations