INDEX

Explanations

conversational elements and responses in a discussion

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

Ð¾Ð·Ñı

-0.16

-anchor

-0.16

 má»ĩnh

-0.14

poz

-0.14

trs

-0.14

ancer

-0.14

obia

-0.13

izzlies

-0.13

idon

-0.13

igt

-0.13

POSITIVE LOGITS

 bounty

0.18

 answer

0.17

Overflow

0.16

ear

0.15

 above

0.15

 sooner

0.14

">//

0.14

.so

0.14

 Answer

0.14

 Woodward

0.14

Activations Density 0.065%

conversational elements and responses in a discussion

No Comments

No Known Activations