INDEX

Explanations

mentions of professional practices and areas of expertise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ãĥ¥

-0.17

canf

-0.15

à¸±à¸Ķ

-0.15

_Tis

-0.15

 Ð²Ð¸Ð½

-0.14

ëĳĺ

-0.14

_Lean

-0.13

áŁĴáŀ

-0.13

}elseif

-0.13

POSITIVE LOGITS

assen

0.19

íĻĪ

0.16

:*

0.15

lif

0.15

globals

0.15

 Lager

0.15

Ø±ÙĬØ³

0.14

zh

0.14

à¸łà¸²à¸¢à¹ĥà¸Ļ

0.14

Activations Density 0.134%

mentions of professional practices and areas of expertise

No Comments

No Known Activations