INDEX

Explanations

forms of the verb "to be" across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ton

-0.19

aro

-0.16

gence

-0.16

tons

-0.15

eum

-0.14

Ð½Ð¸ÑĨÑĮ

-0.14

ÃŃk

-0.14

esse

-0.14

PLEMENT

-0.14

belie

-0.14

POSITIVE LOGITS

/is

0.25

/how

0.24

/w

0.24

 supposed

0.23

/do

0.21

 perceived

0.18

 wont

0.18

/am

0.17

 prÅ¯bÄĽhu

0.17

abouts

0.16

Activations Density 0.106%

forms of the verb "to be" across various contexts

No Comments

No Known Activations