INDEX

Explanations

content headers or structural elements indicating summaries or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

áº±ng

-0.16

ibri

-0.16

ium

-0.15

ague

-0.15

isd

-0.14

çĮ®

-0.14

IMAL

-0.14

atern

-0.14

airo

-0.13

atchet

-0.13

POSITIVE LOGITS

uz

0.15

 Dixon

0.15

 Karel

0.14

Seed

0.14

ed

0.14

urst

0.14

 Wass

0.14

ovna

0.14

 Morton

0.14

à¤µà¤°

0.14

Activations Density 0.052%

content headers or structural elements indicating summaries or descriptions

No Comments

No Known Activations