INDEX

Explanations

locations or places indicated by the word "where."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

lix

-0.16

igor

-0.15

ysl

-0.14

ÑĪÐµ

-0.14

SearchParams

-0.14

\CMS

-0.14

sut

-0.14

erals

-0.14

rome

-0.14

spy

-0.13

POSITIVE LOGITS

upon

0.23

abouts

0.21

ver

0.21

we

0.20

 they

0.19

of

0.19

on

0.19

oping

0.19

it

0.18

unto

0.18

Activations Density 0.087%

locations or places indicated by the word "where."

No Comments

No Known Activations