INDEX

Explanations

phrases indicating the cessation or absence of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eut

-0.17

ãģĭãģªãģĦ

-0.16

 lucky

-0.15

 Narrow

-0.15

yy

-0.15

 blij

-0.14

Orn

-0.14

rella

-0.14

 prone

-0.14

ÙħØ§

-0.14

POSITIVE LOGITS

 anymore

0.16

overy

0.15

 necessarily

0.14

umo

0.14

ÑĤÐ°Ð±

0.14

kÃ³w

0.13

iw

0.13

adays

0.13

odzi

0.13

theless

0.13

Activations Density 0.008%

phrases indicating the cessation or absence of something

No Comments

No Known Activations