INDEX

Explanations

verbs and their variations related to visibility or presence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

oner

-0.19

ENCHMARK

-0.15

zk

-0.15

spir

-0.15

oning

-0.14

ereotype

-0.14

imo

-0.14

holm

-0.14

RNA

-0.14

eter

-0.14

POSITIVE LOGITS

antly

0.24

ances

0.24

/dis

0.22

ees

0.17

åĭ¢

0.16

adox

0.15

ndo

0.15

ìĥĪ

0.15

ance

0.15

ANCES

0.15

Activations Density 0.035%

verbs and their variations related to visibility or presence

No Comments

No Known Activations