INDEX

Explanations

numbers representing decades

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

urette

-0.18

poÄįet

-0.16

icina

-0.15

utut

-0.15

erece

-0.15

icont

-0.15

.SDK

-0.15

ÑģÐ¾Ð»

-0.14

igne

-0.14

urd

-0.14

POSITIVE LOGITS

0.28

å¹´ä»£

0.21

ties

0.19

-'

0.17

decade

0.17

ÅĽci

0.16

es

0.16

ibs

0.16

ies

0.15

/'

0.15

Activations Density 0.017%

numbers representing decades

No Comments

No Known Activations