INDEX

Explanations

phrases indicating actions, changes, or responsibilities in a legal or moral context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

inho

-0.17

ãĤĥ

-0.14

ulis

-0.14

èĲ¥ä¸ļ

-0.14

Mb

-0.14

hos

-0.14

é¨

-0.14

Ã¨ne

-0.14

ÎļÎ±

-0.14

wort

-0.14

POSITIVE LOGITS

mad

0.16

abe

0.15

ilib

0.14

arest

0.14

 targets

0.14

isch

0.14

 Gron

0.13

IEL

0.13

Activations Density 0.004%

phrases indicating actions, changes, or responsibilities in a legal or moral context

No Comments

No Known Activations