INDEX

Explanations

indicators of audience engagement and self-identification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

uez

-0.17

 structural

-0.16

 Structural

-0.16

igsaw

-0.15

ensch

-0.15

addy

-0.15

Ñī

-0.15

ertz

-0.15

rov

-0.14

uala

-0.14

POSITIVE LOGITS

fur

0.18

 jste

0.16

etty

0.16

 yourself

0.15

fur

0.15

.echo

0.14

 hopefully

0.14

 yourselves

0.14

piel

0.14

ãģ¾ãģł

0.14

Activations Density 0.124%

indicators of audience engagement and self-identification

No Comments

No Known Activations