INDEX

Explanations

references to locations and names related to art and culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

adb

-0.15

ãĥķãĤ

-0.15

estre

-0.15

ampo

-0.15

fty

-0.14

itos

-0.14

ynos

-0.14

ëŀĳ

-0.14

weis

-0.14

azon

-0.14

POSITIVE LOGITS

 Structure

0.20

 structure

0.19

YTE

0.18

structure

0.17

Structure

0.17

 crystal

0.17

cop

0.17

 structural

0.16

 refined

0.16

Äįan

0.16

Activations Density 0.030%

references to locations and names related to art and culture

No Comments

No Known Activations