INDEX

Explanations

phrases related to relationships and interpersonal connections

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

ga

-0.15

 taking

-0.15

takes

-0.15

uzu

-0.15

lox

-0.15

annie

-0.14

éł

-0.14

idth

-0.14

uper

-0.14

POSITIVE LOGITS

 seriously

0.23

 hostage

0.22

.setViewport

0.18

 places

0.18

 prisoner

0.17

 Seriously

0.17

 advantage

0.16

 Liberties

0.16

Ð²Ð°Ð»

0.16

_places

0.15

Activations Density 0.032%

phrases related to relationships and interpersonal connections

No Comments

No Known Activations