INDEX

Explanations

terms related to punishment and its implications

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

unma

-0.19

iÃŃ

-0.16

lis

-0.16

igest

-0.15

ouz

-0.15

infeld

-0.15

 winding

-0.15

incinn

-0.15

Scoped

-0.15

iesel

-0.15

POSITIVE LOGITS

0.17

oftware

0.14

nik

0.14

.stub

0.14

ints

0.14

mar

0.13

storybook

0.13

 alcoholic

0.13

aight

0.13

Activations Density 0.067%

terms related to punishment and its implications

No Comments

No Known Activations