INDEX

Explanations

words related to approximations and estimations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

bomb

-0.17

aja

-0.16

ija

-0.15

oh

-0.15

ag

-0.15

FORCE

-0.14

.epam

-0.14

amon

-0.14

 forth

-0.14

holm

-0.14

POSITIVE LOGITS

ÑĩÐ¸Ð½

0.17

ãĥªãĥ¼ãĤº

0.16

sto

0.15

Ð²Ð¸Ð¶

0.15

Î³ÎŃÎ½

0.14

ãĥ¼ãĥ³

0.14

/nginx

0.14

ResultSet

0.14

oons

0.14

ove

0.13

Activations Density 0.014%

words related to approximations and estimations

No Comments

No Known Activations