INDEX

Explanations

punctuation marks and formatting symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ueblo

-0.16

nds

-0.15

apur

-0.15

ayne

-0.15

ayÄ±n

-0.14

.Emit

-0.14

Ø¯Ø§Ø¯

-0.14

wich

-0.13

ovo

-0.13

ayÄ±z

-0.13

POSITIVE LOGITS

Ł³

0.16

Ä©nh

0.14

kke

0.14

stal

0.14

enberg

0.14

iom

0.14

arak

0.14

 Berger

0.14

Utf

0.13

Utf

0.13

Activations Density 0.329%

punctuation marks and formatting symbols

No Comments

No Known Activations