INDEX

Explanations

file formats and document types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

asso

-0.19

amp

-0.15

erman

-0.15

acci

-0.14

Ã³n

-0.14

minus

-0.14

-0.13

 Warn

-0.13

eron

-0.13

ÙĨ

-0.13

POSITIVE LOGITS

MBProgressHUD

0.17

uger

0.16

ancellable

0.15

-INFRINGEMENT

0.14

outu

0.14

owl

0.14

 Surround

0.14

uilder

0.14

/WebAPI

0.14

Forgery

0.14

Activations Density 0.015%

file formats and document types

No Comments

No Known Activations