INDEX

Explanations

references to the word "dim" 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 @ 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

naire

-0.16

zen

-0.16

ificant

-0.15

ame

-0.15

ificate

-0.15

aleza

-0.15

naires

-0.15

athan

-0.15

PFN

-0.15

alg

-0.14

POSITIVE LOGITS

ENSIONS

0.27

Dim

0.27

dim

0.26

Dim

0.25

ENSION

0.25

inished

0.25

dim

0.23

ensions

0.23

ethyl

0.22

,dim

0.21

Activations Density 0.013%

references to the word "dim" and its variations

No Comments

No Known Activations