INDEX

Explanations

names of individuals and their roles or achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

çĴ

-0.15

 Mojo

-0.15

ening

-0.15

;element

-0.14

Ð°ÑĤÑĥ

-0.14

esti

-0.14

Falsy

-0.13

ÐµÐ´Ð¶

-0.13

Gap

-0.13

çį²

-0.13

POSITIVE LOGITS

agus

0.18

ĨĴ

0.15

ãĥ¥ãĥ¼

0.14

obraz

0.13

oka

0.13

blend

0.13

uraa

0.13

imator

0.13

inished

0.13

OURS

0.13

Activations Density 0.103%

names of individuals and their roles or achievements

No Comments

No Known Activations