INDEX

Explanations

terms related to specific cultural or media references

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ampus

-0.16

 Bans

-0.15

olet

-0.14

olver

-0.14

.bio

-0.14

smart

-0.14

_nth

-0.13

ä¹ħä¹ħ

-0.13

bio

-0.13

pery

-0.13

POSITIVE LOGITS

ickey

0.17

yny

0.16

enny

0.16

 rewards

0.16

ÐºÐ°Ð²

0.15

 reward

0.15

$MESS

0.15

 Socialist

0.15

Bay

0.14

ubber

0.14

Activations Density 0.011%

terms related to specific cultural or media references

No Known Activations