INDEX

Explanations

references to variable definitions and shell command syntax

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

ixin

-0.17

ess

-0.17

ees

-0.16

APPER

-0.16

etary

-0.14

joy

-0.14

.WinForms

-0.14

 modelAndView

-0.13

elry

-0.13

cctor

-0.13

POSITIVE LOGITS

_perms

0.15

lique

0.15

ahr

0.14

Ú©Ø±

0.14

0.13

PM

0.13

JC

0.13

erli

0.13

Activations Density 0.015%

references to variable definitions and shell command syntax

No Comments

No Known Activations