INDEX

Explanations

mentions of respect and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

inality

-0.16

ondo

-0.16

oma

-0.16

elim

-0.15

elop

-0.15

eree

-0.15

alysis

-0.14

ÌĢ

-0.14

icter

-0.14

igkeit

-0.14

POSITIVE LOGITS

ably

0.26

ibly

0.15

habi

0.15

ively

0.15

.bootstrapcdn

0.14

ible

0.14

mund

0.14

fully

0.14

imonial

0.13

odata

0.13

Activations Density 0.033%

mentions of respect and its variations in various contexts

No Comments

No Known Activations