INDEX

Explanations

terms related to language, communication, and expression of diverse perspectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

.xtext

-0.17

IXEL

-0.16

.ptr

-0.14

è¼

-0.14

ÎµÎ»

-0.13

eld

-0.13

ams

-0.13

ajar

-0.13

uppe

-0.13

emy

-0.13

POSITIVE LOGITS

 besides

1.08

 aside

0.93

 apart

0.90

bes

0.75

 Besides

0.73

 alÃ©m

0.71

 Apart

0.71

 beyond

0.70

aside

0.68

éĻ¤äºĨ

0.68

Activations Density 0.462%

terms related to language, communication, and expression of diverse perspectives

No Comments

No Known Activations