INDEX

Explanations

terms related to pets or animals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

atta

-0.20

ividual

-0.16

ventario

-0.16

hma

-0.15

åĴ²

-0.15

ystate

-0.15

rette

-0.15

umber

-0.15

 Hind

-0.15

edImage

-0.15

POSITIVE LOGITS

ting

0.18

ucci

0.18

eh

0.18

ted

0.17

ego

0.16

abytes

0.15

roleum

0.15

abyte

0.15

amy

0.14

ohl

0.14

Activations Density 0.029%

terms related to pets or animals

No Comments

No Known Activations