INDEX

Explanations

numerical patterns and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

  ↵  ↵

-0.24

Body

-0.17

 Kendrick

-0.16

acre

-0.16

/read

-0.16

fully

-0.15

Øª

-0.15

sections

-0.15

ly

-0.15

aware

-0.15

POSITIVE LOGITS

../../../

0.18

-ÑĤÐ¾

0.17

/xhtml

0.17

ers

0.17

-ÑĤÐ°ÐºÐ¸

0.17

er

0.16

veh

0.15

asil

0.15

stÃ¥

0.14

Activations Density 0.327%

numerical patterns and references

No Comments

No Known Activations