INDEX

Explanations

references to blindness and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ilos

-0.17

ãĤ«ãĥ«

-0.15

ldkf

-0.15

undry

-0.15

oka

-0.15

aved

-0.15

ifice

-0.15

ÑĪÐºÑĥ

-0.15

eru

-0.14

erence

-0.14

POSITIVE LOGITS

fold

0.50

-fold

0.32

spot

0.31

Fold

0.30

 folded

0.29

spots

0.28

 Fold

0.28

 spot

0.28

 fold

0.28

 spots

0.27

Activations Density 0.007%

references to blindness and related concepts

No Comments

No Known Activations