INDEX

Explanations

terms related to public speaking and speaker engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

YP

-0.15

imers

-0.15

ATRIX

-0.14

Nos

-0.14

Nos

-0.14

ÐŁÐļ

-0.14

 Rear

-0.14

ops

-0.14

ÙĨØ¯ÛĮ

-0.14

 Merry

-0.13

POSITIVE LOGITS

 booking

0.21

 hire

0.19

 Booking

0.19

 agent

0.18

 Speaker

0.17

Spe

0.17

 contact

0.17

 Hire

0.17

agent

0.16

 speaking

0.16

Activations Density 0.002%

terms related to public speaking and speaker engagement

No Comments

No Known Activations