INDEX

Explanations

terms related to admiration or affection

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

uestos

-0.14

edo

-0.14

eba

-0.14

 LOSS

-0.14

canf

-0.13

uesto

-0.13

åĸĦ

-0.13

urb

-0.13

éĬ·

-0.13

POSITIVE LOGITS

anne

0.16

oux

0.16

anine

0.16

abel

0.15

ity

0.15

 contributor

0.14

 Wald

0.14

 Downs

0.14

iotic

0.14

 fully

0.14

Activations Density 0.007%

terms related to admiration or affection

No Comments

No Known Activations