INDEX

Explanations

financial metrics and statistics related to specific years and terms

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

idot

-0.16

Î¹Îº

-0.15

resh

-0.15

Î¸Î¹

-0.15

 migrationBuilder

-0.15

ungi

-0.14

 æī

-0.14

ided

-0.14

ÙĥÙĬ

-0.14

istar

-0.14

POSITIVE LOGITS

annis

0.15

.rs

0.15

yon

0.15

alama

0.14

Äįet

0.14

uar

0.14

å°ļ

0.14

pto

0.14

xeb

0.14

ivan

0.14

Activations Density 0.351%

financial metrics and statistics related to specific years and terms

No Comments

No Known Activations