INDEX

Explanations

programming-related references, particularly code structure and file inclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

iesen

-0.15

ÐµÐ¹Ð½

-0.15

zÄĻ

-0.15

CEF

-0.14

auses

-0.14

 aktual

-0.14

iggs

-0.14

ekk

-0.14

rana

-0.14

istar

-0.14

POSITIVE LOGITS

 Escort

0.16

abel

0.15

 fluid

0.15

 abstract

0.14

 Estr

0.14

nip

0.14

 fantasy

0.14

peÄį

0.13

 stem

0.13

cav

0.13

Activations Density 0.004%

programming-related references, particularly code structure and file inclusions

No Comments

No Known Activations