INDEX

Explanations

terms related to design and construction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

onest

-0.14

STYPE

-0.14

ataire

-0.14

inite

-0.14

udden

-0.13

.uml

-0.13

alls

-0.13

OWL

-0.13

TERS

-0.13

aur

-0.13

POSITIVE LOGITS

 around

0.34

 specifically

0.29

 especially

0.29

to

0.29

around

0.26

 expressly

0.26

 keeping

0.25

for

0.24

so

0.24

 with

0.24

Activations Density 0.079%

terms related to design and construction

No Comments

No Known Activations