INDEX

Explanations

references to carbon and its various contexts, such as emissions and capture technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

æ³ķäºº

-0.19

lero

-0.15

ingly

-0.14

gli

-0.14

argar

-0.14

upy

-0.14

 ÙĤØ§Ø¨

-0.14

egrator

-0.14

ÙĬÙĨØ©

-0.14

ection

-0.13

POSITIVE LOGITS

 dioxide

0.44

aceous

0.33

 footprint

0.30

-neutral

0.28

 neutrality

0.25

 neutral

0.25

ifer

0.25

ated

0.25

mon

0.24

 capture

0.24

Activations Density 0.013%

references to carbon and its various contexts, such as emissions and capture technologies

No Comments

No Known Activations