INDEX

Explanations

expressions of generality or inclusiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

çļĦæĺ¯

-0.18

 each

-0.17

pper

-0.17

led

-0.16

 stuff

-0.16

 Things

-0.16

 Various

-0.16

 things

-0.15

chio

-0.15

stu

-0.15

POSITIVE LOGITS

/all

0.42

THING

0.31

 kind

0.29

place

0.29

ones

0.27

 sort

0.26

thin

0.25

kind

0.24

where

0.23

ht

0.23

Activations Density 0.095%

expressions of generality or inclusiveness

No Comments

No Known Activations