INDEX

Explanations

terms related to tolerance and intolerance

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

icular

-0.21

ic

-0.20

resse

-0.19

ropol

-0.17

ery

-0.16

uchar

-0.16

/perl

-0.15

nid

-0.15

oria

-0.15

ichi

-0.15

POSITIVE LOGITS

 tolerance

0.34

 toler

0.33

 tolerate

0.29

 tolerant

0.27

tol

0.27

ances

0.26

ably

0.25

_tolerance

0.24

able

0.24

 intoler

0.24

Activations Density 0.011%

terms related to tolerance and intolerance

No Comments

No Known Activations