INDEX

Explanations

proper nouns and titles related to people and positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

emple

-0.15

aln

-0.14

innacle

-0.14

moh

-0.14

achu

-0.14

oux

-0.14

volution

-0.13

ocl

-0.13

oulos

-0.13

POSITIVE LOGITS

ä½ľä¸º

0.24

 onto

0.21

 sebagai

0.20

 into

0.20

onto

0.19

çĤº

0.19

ä¸º

0.18

into

0.17

uts

0.17

to

0.17

Activations Density 0.147%

proper nouns and titles related to people and positions

No Comments

No Known Activations