INDEX

Explanations

references to versions and components of the Java programming language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ity

-0.17

lea

-0.17

ng

-0.16

ouser

-0.15

oller

-0.15

ingleton

-0.15

urai

-0.15

elves

-0.15

 Leban

-0.15

self

-0.14

POSITIVE LOGITS

.lang

0.30

FX

0.27

SE

0.26

EE

0.25

EE

0.25

SE

0.23

.util

0.23

/lang

0.23

.Lang

0.22

.awt

0.22

Activations Density 0.031%

references to versions and components of the Java programming language

No Comments

No Known Activations