INDEX

Explanations

references to social media follower counts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

lope

-0.15

izik

-0.14

ABA

-0.14

çİĦ

-0.14

bul

-0.14

IOUS

-0.14

tsx

-0.14

tee

-0.14

olit

-0.14

.Metro

-0.13

POSITIVE LOGITS

pard

0.15

ati

0.15

uÃ©

0.15

QS

0.14

COND

0.14

eniable

0.14

ãĤ¤ãĤ¹

0.13

iÃŁ

0.13

.hasNext

0.13

Activations Density 0.009%

references to social media follower counts

No Comments

No Known Activations