INDEX

Explanations

references to reading or viewing content

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

ocket

-0.16

 slee

-0.15

ogan

-0.15

uns

-0.15

atar

-0.15

 dich

-0.15

ivnÃŃ

-0.14

æĿŁ

-0.14

tom

-0.14

uggage

-0.14

POSITIVE LOGITS

_outline

0.16

zell

0.16

 pres

0.16

STACK

0.15

uraa

0.14

strstr

0.14

 Laden

0.14

{*

0.14

nict

0.14

 strstr

0.14

Activations Density 0.247%

references to reading or viewing content

No Comments

No Known Activations