INDEX

Explanations

terms related to hospitality and acceptance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

zelf

-0.18

 objectMapper

-0.17

ched

-0.17

utin

-0.15

ernals

-0.15

uelle

-0.15

ophile

-0.15

jal

-0.15

rv

-0.15

nm

-0.14

POSITIVE LOGITS

 aboard

0.24

 into

0.20

/welcome

0.20

 addition

0.18

-home

0.18

_into

0.18

 Into

0.17

 ance

0.17

 Addition

0.17

 back

0.16

Activations Density 0.030%

terms related to hospitality and acceptance

No Comments

No Known Activations