INDEX

Explanations

terms related to the processing and handling of information or materials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

indow

-0.20

-0.16

.ACCESS

-0.15

GORITH

-0.15

yre

-0.14

hiro

-0.14

he

-0.14

 petty

-0.14

enty

-0.14

roz

-0.14

POSITIVE LOGITS

sing

0.26

ors

0.26

ional

0.25

ual

0.20

ions

0.20

EDURE

0.19

urement

0.19

.cwd

0.19

sed

0.19

UAL

0.18

Activations Density 0.023%

terms related to the processing and handling of information or materials

No Comments

No Known Activations