INDEX

Explanations

times or timestamps

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

umas

-0.18

Interop

-0.15

Leh

-0.14

 Standing

-0.14

 doctrines

-0.14

ovic

-0.14

å·±

-0.13

amping

-0.13

 mile

-0.13

leh

-0.13

POSITIVE LOGITS

DESC

0.15

apel

0.15

ç¥Ń

0.14

uell

0.14

.fromJson

0.14

PLE

0.14

Ð¾ÑĤÑĢÐµÐ±

0.14

å»³

0.13

tach

0.13

elm

0.13

Activations Density 0.002%

times or timestamps

No Comments

No Known Activations