INDEX

Explanations

words related to safety in activities or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

omb

-0.18

 Suites

-0.18

ft

-0.16

zie

-0.15

↵

-0.15

dom

-0.14

 retain

-0.14

Umb

-0.14

 Companion

-0.14

_plugin

-0.14

POSITIVE LOGITS

.Encoding

0.15

 blind

0.15

blind

0.15

ichel

0.14

asyarak

0.14

odka

0.14

 Ð²Ð½ÐµÑģ

0.14

UGE

0.14

Î³ÏĮ

0.14

PTS

0.14

Activations Density 0.371%

words related to safety in activities or events

No Comments

No Known Activations