INDEX

Explanations

terminology related to deception and false narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

hlen

-0.20

-0.15

å½¦

-0.15

china

-0.15

andon

-0.14

éĽĦ

-0.14

ADS

-0.14

 Rated

-0.14

°

-0.14

-0.13

POSITIVE LOGITS

 unto

0.25

rather

0.20

 rather

0.20

Rather

0.19

 Rather

0.19

 affair

0.18

 meant

0.15

mas

0.15

 Ð²Ð¾Ð²

0.15

>{!!

0.15

Activations Density 0.316%

terminology related to deception and false narratives

No Comments

No Known Activations