INDEX

Explanations

phrases indicating a sense of obligation or dependency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

tÃ¼

-0.17

auen

-0.15

veis

-0.15

aiser

-0.14

zeich

-0.14

.mag

-0.14

auf

-0.13

anik

-0.13

ÅĽci

-0.13

createView

-0.13

POSITIVE LOGITS

us

0.23

 them

0.20

 many

0.18

us

0.17

usat

0.16

him

0.16

 everyone

0.15

usan

0.14

 Spar

0.14

 those

0.14

Activations Density 0.149%

phrases indicating a sense of obligation or dependency

No Comments

No Known Activations