INDEX

Explanations

programming-related expressions and operations

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

-0.18

aab

-0.16

duk

-0.16

-0.15

rend

-0.15

-0.14

rim

-0.14

acci

-0.14

Duy

-0.14

 neat

-0.14

POSITIVE LOGITS

Ģìŀ¥

0.17

æ£ļ

0.15

 Junction

0.14

CALE

0.14

anse

0.14

.SM

0.14

 ÙģØ§Ø±

0.14

ushman

0.14

çī

0.14

stown

0.13

Activations Density 0.271%

programming-related expressions and operations

No Comments

No Known Activations