INDEX

Explanations

occurrences of the word "to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

aju

-0.15

cono

-0.15

zcze

-0.15

à¹Īà¸ĩ

-0.14

ADING

-0.14

Ð·ÑĮ

-0.14

ersen

-0.14

Ars

-0.14

[$_

-0.14

anela

-0.13

POSITIVE LOGITS

seg

0.17

ppv

0.15

 Bened

0.14

anche

0.14

bs

0.13

Sexy

0.13

_STATIC

0.13

_syntax

0.13

cen

0.13

Activations Density 0.019%

occurrences of the word "to."

No Comments

No Known Activations