INDEX

Explanations

expressions of success or positive outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

omor

-0.15

anik

-0.15

alom

-0.15

 Attribution

-0.15

ovah

-0.15

gth

-0.14

deaux

-0.14

isco

-0.14

à¹Ħà¸Ĺà¸¢

-0.14

 Integrity

-0.14

POSITIVE LOGITS

 Ø¨Ùĥ

0.14

 Ð¿Ð¾Ð´Ð²

0.14

iated

0.14

strate

0.13

 ÑįÑĤ

0.13

Por

0.13

 reachable

0.13

nable

0.13

idd

0.13

CTYPE

0.13

Activations Density 0.000%

expressions of success or positive outcomes

No Comments

No Known Activations