INDEX

Explanations

references to specific products and their features, particularly related to motorcycles and video games

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

shal

-0.17

.Aggressive

-0.14

vise

-0.14

abay

-0.13

gf

-0.13

 ÑģÐ¾ÑģÑĤ

-0.13

@mail

-0.13

buz

-0.13

 Ø§ÙĦØ£ØŃ

-0.13

uan

-0.13

POSITIVE LOGITS

ibi

0.16

ÐµÐºÐ°ÑĢ

0.14

readystatechange

0.13

IID

0.13

Ã³w

0.13

roker

0.13

acro

0.13

å±ĭ

0.13

erten

0.12

à¸Ńà¸Ķ

0.12

Activations Density 0.148%

references to specific products and their features, particularly related to motorcycles and video games

No Comments

No Known Activations