INDEX

Explanations

specific high-frequency nouns and values in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

opensource

-0.15

ydk

-0.15

¯

-0.15

ythe

-0.14

Ð¶Ð¸Ð²

-0.14

 SUBSTITUTE

-0.14

ccione

-0.14

ÑĩÐ¸Ð¹

-0.13

.githubusercontent

-0.13

 ADVISED

-0.13

POSITIVE LOGITS

 Hubbard

0.15

ateg

0.14

unta

0.14

agle

0.14

 Hugh

0.14

eneg

0.14

tout

0.14

umb

0.13

 wire

0.13

fram

0.13

Activations Density 0.002%

specific high-frequency nouns and values in the text

No Comments

No Known Activations