INDEX

Explanations

terms and phrases associated with measurements or quantities related to bias and estimations in experimental contexts

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

 Holy

-0.17

Hol

-0.17

adin

-0.17

HOL

-0.16

Holy

-0.16

Hol

-0.15

holm

-0.15

uko

-0.14

ÏģÏİÎ½

-0.14

 holy

-0.14

POSITIVE LOGITS

del

0.16

born

0.16

 World

0.15

 world

0.15

Del

0.15

 Born

0.14

DEL

0.14

-born

0.14

Ð°Ð»Ñĥ

0.14

world

0.14

Activations Density 0.003%

terms and phrases associated with measurements or quantities related to bias and estimations in experimental contexts

No Comments

No Known Activations