INDEX

Explanations

phrases related to the act of removing or eliminating something

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

quer

-0.17

 mÃ¼ÅŁ

-0.16

olean

-0.16

vos

-0.15

 Julius

-0.14

Gad

-0.14

velle

-0.14

reff

-0.14

atoi

-0.14

oker

-0.14

POSITIVE LOGITS

0.20

ists

0.16

tee

0.16

erse

0.15

ights

0.15

trace

0.14

ulty

0.14

-inf

0.14

 Chuck

0.14

uw

0.14

Activations Density 0.002%

phrases related to the act of removing or eliminating something

No Comments

No Known Activations