INDEX

Explanations

statements and claims regarding events or actions

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

FromClass

-0.17

plist

-0.17

ÑĢÐ¸Ñĩ

-0.14

crement

-0.14

ì¹´ëĿ¼

-0.14

AuthProvider

-0.14

}->

-0.14

riott

-0.13

isko

-0.13

ictor

-0.13

POSITIVE LOGITS

anga

0.14

 UITableViewController

0.14

ulate

0.14

ollipop

0.14

ucht

0.14

onga

0.14

ellaneous

0.13

AU

0.13

eration

0.13

avage

0.13

Activations Density 0.094%

statements and claims regarding events or actions

No Comments

No Known Activations