INDEX

Explanations

phrases or structures indicating a strong connection or relationship between people or concepts

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

ung

-0.16

ed

-0.15

lite

-0.15

ur

-0.15

ln

-0.15

ling

-0.14

 Couple

-0.14

ableView

-0.14

edReader

-0.14

light

-0.14

POSITIVE LOGITS

readcr

0.19

/all

0.17

SenderId

0.15

.BackgroundImageLayout

0.15

gratis

0.15

itchen

0.14

_fds

0.14

Rnd

0.14

utor

0.14

oran

0.13

Activations Density 0.025%

phrases or structures indicating a strong connection or relationship between people or concepts

No Comments

No Known Activations