INDEX

Explanations

key terms related to discussions about films, important conversations, and platforms for dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ivant

-0.16

.amazonaws

-0.16

eza

-0.15

ziej

-0.14

/DD

-0.14

stÃŃ

-0.14

onas

-0.13

à¸²à¸¢

-0.13

bjerg

-0.13

aup

-0.13

POSITIVE LOGITS

 debate

0.70

 discussion

0.68

 discussions

0.56

 Debate

0.56

 debates

0.56

discussion

0.56

 Discussion

0.52

Discussion

0.49

deb

0.49

 conversation

0.48

Activations Density 0.381%

key terms related to discussions about films, important conversations, and platforms for dialogue

No Comments

No Known Activations