INDEX

Explanations

punctuation and inquiry-related phrases, especially questions and statements of wonder

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ophon

-0.16

èĤ¥

-0.15

ãĥ¼ãĥĢ

-0.14

itou

-0.14

isha

-0.14

ÑĥÑħ

-0.14

ritch

-0.13

GetCurrent

-0.13

caff

-0.13

oders

-0.13

POSITIVE LOGITS

 what

0.30

how

0.27

 whom

0.26

why

0.25

who

0.24

How

0.23

 What

0.23

what

0.22

 which

0.22

 where

0.20

Activations Density 0.094%

punctuation and inquiry-related phrases, especially questions and statements of wonder

No Comments

No Known Activations