INDEX

Explanations

occurrences of the word "single" and its variations

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

soever

-0.16

iju

-0.16

sj

-0.16

gard

-0.15

DefaultValue

-0.15

rans

-0.15

lant

-0.14

etten

-0.14

yang

-0.14

en

-0.14

POSITIVE LOGITS

tons

0.49

/single

0.33

-handed

0.26

TON

0.25

ChildScrollView

0.24

(single

0.23

-minded

0.23

-single

0.22

ton

0.21

/group

0.21

Activations Density 0.037%

occurrences of the word "single" and its variations

No Comments

No Known Activations