INDEX

Explanations

abstract concepts and qualities associated with complexity, uniqueness, and transparency

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ysz

-0.18

 EÅŁ

-0.16

ingu

-0.15

Ã²

-0.15

out

-0.15

zi

-0.14

Çİ

-0.14

sv

-0.14

words

-0.14

ÑĩÐ¸ÐºÐ°

-0.14

POSITIVE LOGITS

gger

0.16

ously

0.15

esterday

0.15

enedor

0.14

ipur

0.14

anten

0.14

ustil

0.14

olson

0.14

udades

0.14

Activations Density 0.381%

abstract concepts and qualities associated with complexity, uniqueness, and transparency

No Comments

No Known Activations