INDEX

Explanations

phrases expressing expectations or obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

strar

-0.16

opensource

-0.16

amble

-0.15

ÑİÑģÑĮ

-0.14

ormsg

-0.14

ailer

-0.14

Î¼ÎµÎ½

-0.14

emer

-0.14

aris

-0.14

POSITIVE LOGITS

aks

0.15

modo

0.15

ering

0.14

ON

0.14

ero

0.14

ÐµÑĢÐ²

0.14

Symbol

0.14

è±¡

0.14

LY

0.14

UDO

0.13

Activations Density 0.018%

phrases expressing expectations or obligations

No Comments

No Known Activations