INDEX

Explanations

phrases that indicate signs of change or shifts in societal or political dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

egrity

-0.16

.opens

-0.15

 silence

-0.14

ãģĤãģĴ

-0.14

ãģªãĤĭ

-0.14

cour

-0.14

 Silence

-0.13

_Detail

-0.13

ÏĥÎ¹Î±

-0.13

POSITIVE LOGITS

how

0.26

 ÑģÐ¾Ð±Ð¾Ð¹

0.21

omething

0.20

 something

0.20

 intent

0.20

why

0.18

 intents

0.17

how

0.17

ä¸Ģç§į

0.17

 where

0.16

Activations Density 0.300%

phrases that indicate signs of change or shifts in societal or political dynamics

No Comments

No Known Activations