INDEX

Explanations

phrases indicating 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 @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ãĥ

-0.20

azon

-0.16

å§«

-0.16

hiba

-0.15

ymm

-0.15

axon

-0.14

igmat

-0.14

phis

-0.14

nos

-0.14

estroy

-0.14

POSITIVE LOGITS

got

0.23

Got

0.23

Got

0.21

got

0.18

GOT

0.17

 here

0.16

zen

0.16

 probably

0.15

here

0.15

 exactly

0.15

Activations Density 0.087%

phrases indicating assistance or support

No Comments

No Known Activations