INDEX

Explanations

the repetition of the word "just."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ught

-0.17

ody

-0.17

?p

-0.17

Ø¨Ø³

-0.16

akin

-0.16

agan

-0.15

UGHT

-0.15

razier

-0.15

ODY

-0.14

anic

-0.14

POSITIVE LOGITS

ifications

0.26

ifiable

0.25

ifi

0.25

ifying

0.23

ifies

0.22

IFI

0.22

ification

0.20

iciary

0.20

ifiers

0.19

ifica

0.18

Activations Density 0.054%

the repetition of the word "just."

No Comments

No Known Activations