INDEX

Explanations

expressions of encouragement or gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

bang

-0.18

utenberg

-0.17

_Version

-0.16

Ø§ÙĨØ§

-0.16

lood

-0.15

ebi

-0.15

ÑĩÐ°ÑĤ

-0.15

ems

-0.15

ugo

-0.15

ags

-0.14

POSITIVE LOGITS

 vice

0.15

 meaningful

0.14

phe

0.14

ascar

0.14

VP

0.13

 meaning

0.13

Structured

0.13

 Ø¯Ø§ÙĨÙĦÙĪØ¯

0.13

è¶³

0.13

Sah

0.13

Activations Density 0.119%

expressions of encouragement or gratitude

No Comments

No Known Activations