INDEX

Explanations

technical terms and concepts related to software development processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

bol

-0.14

è²

-0.14

ael

-0.14

 Rubin

-0.14

 bush

-0.14

wij

-0.14

REF

-0.13

 Kurum

-0.13

ivol

-0.13

ROP

-0.13

POSITIVE LOGITS

edia

0.15

atron

0.15

Invoker

0.15

shed

0.15

å¯¸

0.14

.scalablytyped

0.14

 shed

0.14

adio

0.14

Cob

0.14

 Shed

0.14

Activations Density 0.074%

technical terms and concepts related to software development processes

No Comments

No Known Activations