INDEX

Explanations

special character indicators or formatting cues in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

andi

-0.16

oman

-0.15

 Aaron

-0.15

lich

-0.15

 stick

-0.15

uger

-0.14

bole

-0.14

Paz

-0.14

 Gard

-0.14

Aaron

-0.14

POSITIVE LOGITS

.SDK

0.17

æīį

0.16

ansk

0.15

ALA

0.15

 Mein

0.15

stoff

0.15

CHASE

0.14

reuse

0.14

atz

0.14

ascade

0.14

Activations Density 0.002%

special character indicators or formatting cues in text

No Comments

No Known Activations