INDEX

Explanations

emotional expressions and pleas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

.Fat

-0.15

âĸį

-0.14

 ê¶ģ

-0.14

ï»¿#

-0.14

EH

-0.14

LÄ°

-0.14

reff

-0.14

 dáº«n

-0.14

ofilm

-0.14

Ø¨ÛĮØ±

-0.14

POSITIVE LOGITS

NOW

0.14

chie

0.14

£

0.14

sq

0.13

bes

0.13

eed

0.13

áº¡i

0.13

split

0.13

 gotta

0.12

sku

0.12

Activations Density 0.211%

emotional expressions and pleas

No Comments

No Known Activations