INDEX

Explanations

occurrences of punctuation marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ech

-0.15

Ð²Ð°Ð½Ð¾

-0.14

leet

-0.14

_cast

-0.14

ucus

-0.14

leur

-0.13

éĶĢ

-0.13

plusplus

-0.13

iel

-0.13

ione

-0.13

POSITIVE LOGITS

ãĥĥãĥĦ

0.17

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.17

 æŃ£

0.14

cir

0.14

ÏĦÎ¹Ïĥ

0.14

âĤ

0.13

andes

0.13

hone

0.13

 ÃĤ

0.13

ningen

0.13

Activations Density 0.042%

occurrences of punctuation marks

No Comments

No Known Activations