INDEX

Explanations

instances of the word "shift" and its variations, indicating a focus on changes or transitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

erate

-0.16

uento

-0.15

ilet

-0.15

lek

-0.14

hide

-0.14

åĤĻ

-0.14

eled

-0.14

ervation

-0.14

hek

-0.14

ITY

-0.14

POSITIVE LOGITS

shift

0.21

 Shift

0.21

 shifts

0.20

 shift

0.20

 sands

0.19

(shift

0.19

SHIFT

0.19

Shift

0.19

-shift

0.19

 Hlav

0.17

Activations Density 0.017%

instances of the word "shift" and its variations, indicating a focus on changes or transitions

No Comments

No Known Activations