INDEX

Explanations

elements related to form inputs in code

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

ilib

-0.19

ContentLoaded

-0.16

avit

-0.15

inous

-0.15

 Petty

-0.14

/modal

-0.14

isch

-0.14

act

-0.14

Ã¡hl

-0.14

 Park

-0.14

POSITIVE LOGITS

mus

0.15

 placeholder

0.15

Mus

0.15

pell

0.15

MAP

0.15

 required

0.14

ime

0.14

CED

0.14

Tin

0.14

anka

0.14

Activations Density 0.013%

elements related to form inputs in code

No Comments

No Known Activations