INDEX

Explanations

repeated phrases or keywords in varying contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

earn

-0.20

ponent

-0.17

Kou

-0.15

ught

-0.14

usi

-0.14

ogs

-0.14

 Earn

-0.14

ETO

-0.13

ee

-0.13

 Tooth

-0.13

POSITIVE LOGITS

.LoggerFactory

0.17

ume

0.16

ikk

0.15

·

0.15

à¥ĩà¤¯

0.15

¶Į

0.14

Î±Ïĥ

0.14

isen

0.14

 Bark

0.14

iez

0.14

Activations Density 0.051%

repeated phrases or keywords in varying contexts

No Comments

No Known Activations