INDEX

Explanations

references to personal narratives or memoirs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

jer

-0.17

Dao

-0.16

kop

-0.14

æ®

-0.14

ertz

-0.14

Ð»ÐµÑĢ

-0.14

 thumbs

-0.13

oom

-0.13

seau

-0.13

æĮ

-0.13

POSITIVE LOGITS

apur

0.17

ãĥªãĤ«

0.17

enco

0.16

Å¾il

0.15

Ã¤ter

0.15

 Distance

0.15

-invalid

0.14

kker

0.14

Ã¤s

0.14

/Branch

0.14

Activations Density 0.239%

references to personal narratives or memoirs

No Comments

No Known Activations