INDEX

Explanations

references to involvement or connections between different entities or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

antine

-0.14

oped

-0.14

anky

-0.13

amat

-0.13

alus

-0.13

opt

-0.13

å¹´çļĦ

-0.13

hue

-0.13

ä¿

-0.13

 Ø·ÛĮ

-0.13

POSITIVE LOGITS

 among

0.91

 amongst

0.81

among

0.81

 Among

0.70

Among

0.65

 ÑģÑĢÐµÐ´Ð¸

0.54

etc

0.35

 ÙĪØºÙĬØ±

0.34

åħ¶ä¸Ń

0.32

 notamment

0.32

Activations Density 0.178%

references to involvement or connections between different entities or groups

No Comments

No Known Activations