INDEX

Explanations

phrases indicating completeness or totality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

jte

-0.17

jen

-0.16

ebi

-0.16

jem

-0.16

ansen

-0.15

zsche

-0.15

ziel

-0.14

ennes

-0.14

zelf

-0.14

ML

-0.14

POSITIVE LOGITS

erton

0.32

 fled

0.30

 blown

0.30

ledged

0.29

eren

0.29

/full

0.29

-length

0.28

-scale

0.28

filled

0.28

stÃ¤nd

0.28

Activations Density 0.057%

phrases indicating completeness or totality

No Comments

No Known Activations