INDEX

Explanations

references to videos

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iant

-0.16

vel

-0.15

Ĭ

-0.15

aven

-0.15

æ¶

-0.15

bes

-0.14

ivel

-0.14

oten

-0.14

both

-0.14

caff

-0.14

POSITIVE LOGITS

ÐµÐ³Ð¾ÑĢ

0.17

ç²

0.16

.VisualBasic

0.15

ÑĢÑĥÑĩ

0.15

mith

0.15

emade

0.15

oleon

0.15

ÑĥÐ¶Ðµ

0.15

oro

0.14

 DateTimeKind

0.14

Activations Density 0.028%

references to videos

No Comments

No Known Activations