INDEX

Explanations

words related to dining or food experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

tement

-0.17

iates

-0.15

sth

-0.15

sin

-0.15

iya

-0.14

announce

-0.14

Ð¾ÑģÑĮ

-0.14

ÏĥÎ¹

-0.14

igne

-0.14

esc

-0.14

POSITIVE LOGITS

osaurs

0.27

Din

0.21

esty

0.20

acic

0.19

ning

0.19

ucle

0.18

omite

0.18

asty

0.17

din

0.16

ledi

0.16

Activations Density 0.007%

words related to dining or food experiences

No Comments

No Known Activations