INDEX

Explanations

terms related to data breaches and compromised information

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

ãĥŁãĥ¥

-0.16

 ëĭ¤ìļ´ë°Ľê¸°

-0.14

èŃ¦

-0.14

ordo

-0.14

ÑĤÐ¸Ð¹

-0.14

 modelName

-0.14

ecut

-0.14

 Ders

-0.13

Gst

-0.13

iao

-0.13

POSITIVE LOGITS

 sketch

0.15

bots

0.15

 determined

0.15

plib

0.14

uve

0.14

rans

0.13

 Datos

0.13

itial

0.13

Activations Density 0.042%

terms related to data breaches and compromised information

No Comments

No Known Activations