INDEX

Explanations

technical jargon related to programming and data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

(fileName

-0.20

imeType

-0.20

actionDate

-0.19

numberOf

-0.18

(filePath

-0.18

gL

-0.17

oundingBox

-0.17

mM

-0.17

intColor

-0.17

xF

-0.16

POSITIVE LOGITS

 \↵

0.20

.kwargs

0.19

kwargs

0.19

\↵

0.17

.fetchone

0.16

.logged

0.16

Datetime

0.16

 currentItem

0.16

"\↵

0.16

_kwargs

0.15

Activations Density 0.061%

technical jargon related to programming and data processing

No Comments

No Known Activations