INDEX

Explanations

terms related to origin and identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

aeda

-0.15

reater

-0.13

ilim

-0.13

unate

-0.13

elps

-0.12

 reife

-0.12

itted

-0.12

indered

-0.12

Ð°Ð»Ñĥ

-0.12

POSITIVE LOGITS

 latin

0.31

 deriv

0.22

 substant

0.21

 latina

0.21

 appell

0.21

latin

0.20

 suffix

0.20

 latino

0.20

 signific

0.20

 vocab

0.20

Activations Density 0.037%

terms related to origin and identity

No Comments

No Known Activations