INDEX

Explanations

comparative phrases emphasizing superiority or preference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

-0.17

fty

-0.15

 Ekon

-0.15

umen

-0.14

istrate

-0.14

urai

-0.14

 ëĺĲíķľ

-0.14

ãĤ§

-0.14

lette

-0.13

strar

-0.13

POSITIVE LOGITS

udios

0.15

aja

0.15

udio

0.14

any

0.14

 ever

0.14

\Common

0.14

Ĥ¹

0.14

å»

0.13

mos

0.13

.any

0.13

Activations Density 0.069%

comparative phrases emphasizing superiority or preference

No Comments

No Known Activations