INDEX

Explanations

references to the Java programming language and its related libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oka

-0.17

oit

-0.16

-0.15

alen

-0.15

-UA

-0.14

 ãĥĪ

-0.14

-Un

-0.14

ogan

-0.14

POSITIVE LOGITS

otton

0.16

ÏİÎ½

0.15

CHAT

0.15

ÅĻes

0.15

 Demp

0.14

 Zucker

0.14

wards

0.14

IDA

0.14

ëĿ¼ëıĦ

0.14

elocity

0.14

Activations Density 0.003%

references to the Java programming language and its related libraries

No Comments

No Known Activations