INDEX

Explanations

present tense and past tense forms of the verb "to be."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 itself

-0.16

asin

-0.14

res

-0.14

roker

-0.14

org

-0.14

rier

-0.13

lings

-0.13

acea

-0.13

 jack

-0.13

ate

-0.13

POSITIVE LOGITS

oret

0.18

oretical

0.16

ãģ§ãģĻãģŃ

0.15

 olmadan

0.14

Ø§Ø²ÙĦ

0.14

oku

0.14

 bÃ¶ylece

0.14

olume

0.14

 citiz

0.13

vek

0.13

Activations Density 0.475%

present tense and past tense forms of the verb "to be."

No Comments

No Known Activations