INDEX

Explanations

occurrences of the word "test" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ing

-0.18

htags

-0.15

licas

-0.15

ught

-0.15

geh

-0.15

Ð²Ð¾ÑĢ

-0.15

 Finger

-0.15

readcr

-0.15

oho

-0.15

tingham

-0.14

POSITIVE LOGITS

aments

0.33

imony

0.31

udo

0.28

icular

0.27

imon

0.27

ament

0.27

oster

0.24

AMENT

0.23

imonials

0.23

imonial

0.23

Activations Density 0.023%

occurrences of the word "test" in various contexts

No Comments

No Known Activations