INDEX

Explanations

headings or titles in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

amb

-0.17

ourg

-0.16

vice

-0.15

zig

-0.15

ÛĮØ¯Ø§

-0.14

 Skipping

-0.14

 vice

-0.13

 Spotlight

-0.13

 intox

-0.13

 Vice

-0.13

POSITIVE LOGITS

ppers

0.16

 å°

0.16

nip

0.15

iÃ³

0.15

ãĥ³ãĥ

0.14

ÙģØ§Ø¹

0.14

 Cann

0.14

Ð¾Ð´Ð¸

0.14

undler

0.14

 addCriterion

0.14

Activations Density 0.212%

headings or titles in the text

No Comments

No Known Activations