INDEX

Explanations

requests for assistance or support

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

wers

-0.17

phans

-0.16

er

-0.16

sb

-0.15

achs

-0.15

à¸«à¸¡à¸²à¸¢

-0.15

hed

-0.15

rette

-0.14

æĪ·

-0.14

vette

-0.14

POSITIVE LOGITS

desk

0.22

lessness

0.19

 Äĳá»¡

0.19

ERSHEY

0.17

imm

0.17

lessly

0.17

fully

0.17

ington

0.16

/help

0.16

0.15

Activations Density 0.065%

requests for assistance or support

No Comments

No Known Activations