INDEX

Explanations

occurrences of the word "username" and its variations in context of login processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

igator

-0.16

çĦ¶

-0.14

umen

-0.14

 Dagger

-0.14

za

-0.14

Ð½Ð°Ñĩ

-0.13

 Cunningham

-0.13

 Paren

-0.13

dr

-0.13

imento

-0.13

POSITIVE LOGITS

AndPassword

0.19

rupa

0.17

zug

0.15

ymoon

0.15

 Kurd

0.14

lite

0.14

ettle

0.14

Typed

0.14

deen

0.14

ruba

0.14

Activations Density 0.006%

occurrences of the word "username" and its variations in context of login processes

No Comments

No Known Activations