INDEX

Explanations

references to television shows, streaming services, and online media content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

amar

-0.19

ÑıÐ±

-0.17

inux

-0.15

anton

-0.14

 Fitness

-0.14

ãĥĲãĥ¼

-0.14

lex

-0.14

ipes

-0.14

anh

-0.14

beg

-0.14

POSITIVE LOGITS

icontrol

0.17

ument

0.17

aginator

0.16

 Lance

0.15

hari

0.14

HLT

0.14

 offic

0.14

 ÐĶÐ¸Ð²

0.14

odiac

0.13

hour

0.13

Activations Density 0.231%

references to television shows, streaming services, and online media content

No Comments

No Known Activations