INDEX

Explanations

instances of naming changes or rebranding events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ÑĢÐ´

-0.17

-gradient

-0.16

éĿĴ

-0.14

ÏģÎ¹Î¬

-0.14

 oppos

-0.14

 ÙĪÙĤØª

-0.13

gradient

-0.13

rary

-0.13

fork

-0.13

emin

-0.13

POSITIVE LOGITS

Î¹Ïİ

0.16

'gc

0.16

 Appro

0.15

 observable

0.14

nze

0.14

 trace

0.14

IPH

0.14

 Studios

0.14

sie

0.14

rim

0.13

Activations Density 0.016%

instances of naming changes or rebranding events

No Comments

No Known Activations