INDEX

Explanations

concepts related to classification and categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

“He

-0.24

"He

-0.24

 celui

-0.21

 ÐºÐ¾ÑĤÐ¾ÑĢÑĭÐ¹

-0.19

Î¼ÎŃÎ½Î¿ÏĤ

-0.18

 ÑıÐºÐ¸Ð¹

-0.18

 kterÃ½

-0.18

 byli

-0.17

 ÐºÐ°Ð¶Ð´Ð¾Ð³Ð¾

-0.17

him

-0.17

POSITIVE LOGITS

adas

0.45

 ellas

0.44

 elles

0.44

Ã¡ticas

0.42

å¥¹ä»¬

0.37

elles

0.37

ativas

0.36

Ã©es

0.34

nicas

0.34

 ones

0.34

Activations Density 0.091%

concepts related to classification and categorization

No Comments

No Known Activations