INDEX

Explanations

concepts related to responsibility and accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

lingen

-0.15

lass

-0.14

Ãło

-0.14

 Ãľst

-0.14

okoj

-0.13

Ð¼ÐµÑĩ

-0.13

imers

-0.13

lek

-0.13

LC

-0.13

-Origin

-0.13

POSITIVE LOGITS

 lies

1.02

lie

0.99

 lying

0.79

 Lies

0.76

Lie

0.74

lay

0.69

lie

0.68

lies

0.68

 lied

0.66

Lie

0.66

Activations Density 0.366%

concepts related to responsibility and accountability

No Comments

No Known Activations