INDEX

Explanations

names of companies and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

wr

-0.16

.StackTrace

-0.15

à¸¥à¸°

-0.15

throp

-0.15

OK

-0.14

æ¿

-0.14

KO

-0.14

Ø¨Ø§Ø²

-0.14

odge

-0.14

 Alloy

-0.14

POSITIVE LOGITS

anca

0.16

 reserves

0.15

Ø§Ø±Ø§Øª

0.14

 suck

0.14

vard

0.14

 mandatory

0.14

arf

0.14

iek

0.14

rada

0.14

 Shaun

0.13

Activations Density 0.057%

names of companies and organizations

No Comments

No Known Activations