INDEX

Explanations

words related to legal issues and penalties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

TEL

-0.15

defgroup

-0.15

adil

-0.15

meli

-0.15

çİī

-0.14

zzo

-0.14

ignite

-0.14

 Äĳáº©y

-0.14

uÅ¡

-0.14

agenta

-0.14

POSITIVE LOGITS

amo

0.16

ollo

0.16

 ãĥį

0.15

icha

0.14

conds

0.14

 è¨Ģ

0.13

ÄĽÅ¾

0.13

 pled

0.13

anic

0.13

Activations Density 0.046%

words related to legal issues and penalties

No Comments

No Known Activations