INDEX

Explanations

references to annual metrics or measurements related to financials or performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lessness

-0.15

Ð»ÐµÑĢ

-0.14

Ã³ÅĤ

-0.14

Ã¼hr

-0.14

 ç±

-0.14

amiliar

-0.13

AZY

-0.13

ãģĦãģĨ

-0.13

Sil

-0.13

atte

-0.13

POSITIVE LOGITS

/month

0.21

hone

0.17

ity

0.17

éĳĳ

0.16

-olds

0.15

anta

0.15

stown

0.15

-old

0.15

scoped

0.15

-round

0.15

Activations Density 0.022%

references to annual metrics or measurements related to financials or performance

No Comments

No Known Activations