INDEX

Explanations

terms related to programming interfaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ellt

-0.16

ifen

-0.15

Dag

-0.15

emailer

-0.15

dag

-0.15

.btnSave

-0.15

onitor

-0.14

IDA

-0.14

ÑĤÐ¸Ðº

-0.14

Ä±rak

-0.14

POSITIVE LOGITS

ech

0.17

ÏĦÎ¿Î¹

0.15

 Toll

0.15

 Bowman

0.15

eties

0.15

olland

0.15

ury

0.14

 downstream

0.14

sol

0.14

Activations Density 0.006%

terms related to programming interfaces

No Comments

No Known Activations