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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

forcer

-0.13

jo

-0.12

æ°ı

-0.12

ÃŃ

-0.12

odus

-0.12

gig

-0.12

/svg

-0.11

()

-0.11

ê¸°ê°Ģ

-0.11

POSITIVE LOGITS

etc

0.18

 ÑĤÐ¾ÑīÐ¾

0.17

stringLiteral

0.16

?,

0.16

ALLED

0.14

?,

0.14

egg

0.13

 Erotische

0.13

 MetroFramework

0.13

ï»¿#

0.13

Activations Density 0.203%

names of companies and organizations

No Comments

No Known Activations