INDEX

Explanations

the presence of names and proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

alse

-0.17

ev

-0.16

pl

-0.15

won

-0.14

 Ã½

-0.14

alie

-0.14

abin

-0.13

ALSE

-0.13

uls

-0.13

POSITIVE LOGITS

.addElement

0.16

shm

0.16

ultipart

0.16

raith

0.15

lime

0.15

ingen

0.15

iform

0.15

Ú©Ùħ

0.15

peare

0.14

pect

0.14

Activations Density 0.247%

the presence of names and proper nouns

No Comments

No Known Activations