INDEX

Explanations

elements related to web navigation and scripts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

HexString

-0.16

ologna

-0.15

irut

-0.15

pany

-0.14

igy

-0.14

TouchUpInside

-0.14

nou

-0.14

å¶

-0.14

lop

-0.14

ongyang

-0.13

POSITIVE LOGITS

0.15

Cook

0.15

 Papa

0.14

isex

0.14

sticky

0.14

 Cook

0.14

affer

0.14

 Giov

0.13

ä»°

0.13

ould

0.13

Activations Density 0.012%

elements related to web navigation and scripts

No Comments

No Known Activations