INDEX

Explanations

references to specific types of trees, particularly those including "Cedar."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

otta

-0.17

gens

-0.16

yre

-0.15

ea

-0.15

ALSE

-0.15

enes

-0.15

alse

-0.15

regon

-0.15

å½¹

-0.14

endon

-0.14

POSITIVE LOGITS

 Rapids

0.27

hurst

0.21

rap

0.19

crest

0.19

 Shake

0.18

 Sinai

0.18

 Crest

0.17

 Rapid

0.17

burg

0.17

baum

0.16

Activations Density 0.006%

references to specific types of trees, particularly those including "Cedar."

No Comments

No Known Activations