INDEX

Explanations

connections to pets and their positive or negative implications 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 @ 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

ideographic

-0.16

ajs

-0.16

hetto

-0.14

ellar

-0.14

dete

-0.13

olist

-0.13

("$.

-0.13

urgical

-0.13

_REUSE

-0.13

 chocol

-0.13

POSITIVE LOGITS

 religion

0.33

 medicine

0.31

 politics

0.30

 technology

0.28

 biology

0.25

 photography

0.23

 science

0.23

 commerce

0.23

 mathematics

0.22

technology

0.22

Activations Density 1.114%

connections to pets and their positive or negative implications in various contexts

No Comments

No Known Activations