INDEX

Explanations

instances of the word "this" and related phrases indicating specificity or reference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ader

-0.17

ãģĤãĤĭ

-0.15

sus

-0.15

uncated

-0.14

logen

-0.14

ingen

-0.14

ength

-0.14

agen

-0.13

axies

-0.13

emer

-0.13

POSITIVE LOGITS

way

0.28

 alone

0.24

 again

0.24

can

0.22

is

0.21

 results

0.20

 includes

0.20

 feature

0.19

 then

0.19

 latter

0.19

Activations Density 0.199%

instances of the word "this" and related phrases indicating specificity or reference

No Comments

No Known Activations