INDEX

Explanations

technical terms related to data processing and serialization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 äºĨ

-0.20

äºĨä¸Ģ

-0.19

ised

-0.18

/place

-0.18

ulk

-0.18

iq

-0.18

(ed

-0.15

antly

-0.15

yt

-0.15

POSITIVE LOGITS

ness

0.33

evice

0.22

/generated

0.22

NESS

0.20

epend

0.20

-up

0.20

 Ð½Ð°Ð¼Ð¸

0.19

-out

0.18

icts

0.18

ropping

0.18

Activations Density 1.194%

technical terms related to data processing and serialization

No Comments

No Known Activations