INDEX

Explanations

technical terms related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Pols

-0.15

à¹Ĥ

-0.14

zer

-0.14

ãģ¬

-0.14

acy

-0.13

Assertion

-0.13

den

-0.13

criptor

-0.13

pret

-0.13

POSITIVE LOGITS

elper

0.20

 logger

0.18

ante

0.16

.logger

0.16

obra

0.15

 Logger

0.15

 Pand

0.15

AccessType

0.14

(logger

0.14

Til

0.14

Activations Density 0.872%

technical terms related to programming and data structures

No Comments

No Known Activations