INDEX

Explanations

references to uploaded content or metadata in the document

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

-0.17

ssc

-0.15

Pom

-0.15

ificador

-0.14

neider

-0.14

à¥Ģà¤¦

-0.14

sj

-0.14

 Kore

-0.13

POSITIVE LOGITS

çĴĥ

0.15

atron

0.15

adol

0.15

jac

0.14

uÄį

0.14

#=

0.14

ï¼ģ↵↵

0.14

 alma

0.14

oints

0.14

addtogroup

0.14

Activations Density 0.001%

references to uploaded content or metadata in the document

No Comments

No Known Activations