INDEX

Explanations

references to programming concepts and code structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

phia

-0.18

ClassLoader

-0.16

 guest

-0.16

 Guest

-0.15

éĭ

-0.15

odyn

-0.14

ugal

-0.14

 needle

-0.14

áº¯p

-0.14

ague

-0.13

POSITIVE LOGITS

 header

0.53

 headers

0.45

 Header

0.42

header

0.41

-header

0.39

(header

0.38

Header

0.37

_header

0.36

headers

0.36

å¤´

0.35

Activations Density 0.059%

references to programming concepts and code structure

No Comments

No Known Activations