INDEX

Explanations

programming-related terms and structures within 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.16

æĹĹ

-0.15

ulan

-0.14

omi

-0.14

ruk

-0.14

ÙħÙĤ

-0.14

ãģıãĤĮãģŁ

-0.14

rapper

-0.13

ÙĪÙĤØª

-0.13

 balloons

-0.13

POSITIVE LOGITS

 Bott

0.15

chalk

0.15

 incur

0.15

uo

0.15

 superv

0.15

ãĥ¼ãĥĦ

0.15

Gum

0.14

.uml

0.14

 UNUSED

0.14

ãĥ³ãĤ¯

0.14

Activations Density 0.002%

programming-related terms and structures within the text

No Comments

No Known Activations