INDEX

Explanations

instances of special characters or formatting as well as specific words related to academic or professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

WebpackPlugin

-0.16

 Bray

-0.15

.WriteAll

-0.15

 widened

-0.14

ëĭ´

-0.14

ãģªãģĮ

-0.13

 widening

-0.13

 cover

-0.13

stands

-0.13

braco

-0.13

POSITIVE LOGITS

 separation

0.20

par

0.19

 Separ

0.19

 parasite

0.19

pare

0.18

aldi

0.18

Separ

0.18

epar

0.18

-par

0.17

 Para

0.17

Activations Density 0.014%

instances of special characters or formatting as well as specific words related to academic or professional contexts

No Comments

No Known Activations