INDEX

Explanations

references to discovering new information or experiences online

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 tomorrow

-0.19

eton

-0.16

edia

-0.15

leck

-0.15

-0.14

Ø§Ø¶

-0.14

anch

-0.14

lio

-0.14

 pretend

-0.14

ander

-0.14

POSITIVE LOGITS

_via

0.27

via

0.25

Via

0.21

 recommendation

0.19

via

0.19

recommended

0.19

Via

0.19

åģ¶

0.19

åŃĺäºİ

0.18

æİ¨èįĲ

0.18

Activations Density 0.168%

references to discovering new information or experiences online

No Comments

No Known Activations