INDEX

Explanations

references to source code and related files in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

áº±ng

-0.16

hos

-0.15

ocs

-0.15

laz

-0.14

wire

-0.14

 Kurum

-0.14

kins

-0.14

mailbox

-0.14

rens

-0.14

thic

-0.14

POSITIVE LOGITS

å·»

0.16

orpion

0.16

veloper

0.15

Ñİ

0.15

Ø³Ø§Ø¨

0.15

uddy

0.15

anguard

0.14

 WCHAR

0.14

enou

0.14

-alist

0.14

Activations Density 0.015%

references to source code and related files in a programming context

No Comments

No Known Activations