INDEX

Explanations

terms related to legal definitions and classifications of assaults

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

aub

-0.21

ABL

-0.20

aka

-0.15

ÏģÎ¹Î¬

-0.15

Ð°ÐºÐ°

-0.15

asa

-0.15

ije

-0.14

anÃ§a

-0.14

aud

-0.14

udur

-0.14

POSITIVE LOGITS

 Freund

0.15

ä¹³

0.14

.scalablytyped

0.14

Pit

0.14

itan

0.13

ãĥĮ

0.13

neau

0.13

 versus

0.13

mary

0.13

.observable

0.13

Activations Density 0.003%

terms related to legal definitions and classifications of assaults

No Comments

No Known Activations