INDEX

Explanations

the word "are" in 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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

istra

-0.18

CRET

-0.17

EMS

-0.16

(åľŁ

-0.16

ems

-0.15

 nowrap

-0.15

cision

-0.14

.Css

-0.14

(æľ¨

-0.14

Ã´ng

-0.14

POSITIVE LOGITS

anal

0.16

ollen

0.15

aison

0.14

hu

0.14

oust

0.14

SqlParameter

0.14

 sacr

0.14

 Rath

0.14

 conj

0.14

Activations Density 0.033%

the word "are" in various contexts

No Comments

No Known Activations