INDEX

Explanations

references to specific dates or chronological indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

eln

-0.16

abus

-0.16

cli

-0.15

gili

-0.15

ilton

-0.15

GLOSS

-0.14

akt

-0.14

ires

-0.14

oldt

-0.14

ibal

-0.14

POSITIVE LOGITS

istrovstvÃŃ

0.20

bish

0.16

ipped

0.15

ipping

0.15

itra

0.15

 Swinger

0.15

ÏģÎ¿Î½

0.15

izoph

0.14

rd

0.14

fold

0.14

Activations Density 0.014%

references to specific dates or chronological indicators

No Comments

No Known Activations