INDEX

Explanations

references to the mouth and related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

º«

-0.17

impse

-0.16

hea

-0.15

æ³Ĭ

-0.15

ilt

-0.14

ildo

-0.14

ÎŃÏģ

-0.14

hya

-0.14

å¸Ń

-0.14

ATRIX

-0.14

POSITIVE LOGITS

ful

0.31

piece

0.31

wash

0.27

pieces

0.24

water

0.24

FUL

0.23

 cavity

0.23

-water

0.23

feel

0.22

parts

0.21

Activations Density 0.015%

references to the mouth and related activities

No Comments

No Known Activations