INDEX

Explanations

references to time, particularly durations and specific years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

led

-0.20

ime

-0.18

owitz

-0.17

foy

-0.17

TestFixture

-0.16

ogne

-0.15

Case

-0.15

lesi

-0.15

Ð¾

-0.15

cles

-0.14

POSITIVE LOGITS

 Downing

0.26

acious

0.24

ured

0.23

th

0.21

URED

0.19

acity

0.17

uring

0.17

ase

0.16

ively

0.16

éĥİ

0.15

Activations Density 0.106%

references to time, particularly durations and specific years

No Comments

No Known Activations