INDEX

Explanations

elements of completion and significant events or items within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ani

-0.16

ItemAt

-0.15

arend

-0.15

Ð´Ð¸

-0.15

esome

-0.15

Zot

-0.14

ccione

-0.14

éĽ¶

-0.14

.EntityManager

-0.14

_stuff

-0.14

POSITIVE LOGITS

yk

0.15

yo

0.15

.sax

0.14

ration

0.14

zcze

0.14

addColumn

0.14

hin

0.14

zar

0.14

LOS

0.13

itt

0.13

Activations Density 0.006%

elements of completion and significant events or items within the text

No Comments

No Known Activations