INDEX

Explanations

technical terms and parameters related to programming and class structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

èĩ£

-0.17

nox

-0.15

ÃĹ↵↵

-0.13

ocard

-0.13

ContentView

-0.13

.builders

-0.13

.arguments

-0.13

lt

-0.13

latable

-0.13

imensional

-0.13

POSITIVE LOGITS

readcr

0.17

inea

0.15

kaar

0.15

oir

0.15

 Ãľst

0.15

 Ø¹ÙħÙĦ

0.14

ëĮĢíķľ

0.14

æħİ

0.14

Fro

0.14

inia

0.14

Activations Density 0.055%

technical terms and parameters related to programming and class structures

No Comments

No Known Activations

technical terms and parameters related to programming and class structures

No Comments

No Known Activations