INDEX

Explanations

coding-related concepts, specifically functions and variable definitions

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

orum

-0.17

MT

-0.16

obble

-0.16

abus

-0.15

lingen

-0.14

oload

-0.14

eam

-0.14

Vtbl

-0.14

alach

-0.14

 Hastings

-0.14

POSITIVE LOGITS

wx

0.23

=wx

0.22

(wx

0.20

wx

0.18

AFX

0.17

.wx

0.16

(IDC

0.16

ayer

0.16

IMPLEMENT

0.16

0.15

Activations Density 0.006%

coding-related concepts, specifically functions and variable definitions

No Comments

No Known Activations