INDEX

Explanations

phrases related to communication and speaking interactions

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

conc

-0.16

lette

-0.15

mun

-0.15

 Krank

-0.14

ë§¤

-0.14

 sebe

-0.14

anske

-0.14

utt

-0.14

kop

-0.14

mez

-0.13

POSITIVE LOGITS

 spoke

0.23

 speaking

0.22

 speak

0.21

 Speak

0.21

 spoken

0.20

spe

0.19

Spe

0.19

 Speaking

0.18

 talked

0.17

Speak

0.17

Activations Density 0.032%

phrases related to communication and speaking interactions

No Comments

No Known Activations