INDEX

Explanations

variations of accented characters or symbols 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 @ 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

-0.17

emento

-0.16

iddles

-0.15

Ø¹Ø§Ø¯

-0.14

ÑĮÐ²

-0.14

dont

-0.14

weit

-0.14

ilities

-0.13

ê³µ

-0.13

ainted

-0.13

POSITIVE LOGITS

itable

0.14

eo

0.13

ë¥

0.13

å®Ŀ

0.13

 FindObjectOfType

0.13

iad

0.13

Ùĳ

0.13

 cher

0.13

 exercise

0.13

Bes

0.13

Activations Density 0.081%

variations of accented characters or symbols in text

No Comments

No Known Activations