INDEX

Explanations

instances of the word "additionally" and variations thereof, indicating a focus on supplementary information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 otherwise

-0.17

 first

-0.15

riers

-0.14

equ

-0.14

ries

-0.14

"crypto

-0.14

eken

-0.13

xmax

-0.13

otherwise

-0.13

bart

-0.13

POSITIVE LOGITS

ampo

0.17

TabControl

0.16

çĴ

0.15

ãĥ£

0.15

 importantly

0.14

roz

0.14

ãĤ§

0.14

enes

0.14

onym

0.13

Activations Density 0.011%

instances of the word "additionally" and variations thereof, indicating a focus on supplementary information

No Comments

No Known Activations