INDEX

Explanations

phrases related to moral and ethical behavior

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

bject

-0.17

olini

-0.17

he

-0.15

by

-0.15

ieur

-0.14

imm

-0.14

ayed

-0.14

 Nash

-0.14

 ÙĩØ³Øª

-0.14

POSITIVE LOGITS

ä¾į

0.16

tics

0.15

orch

0.15

wins

0.14

isque

0.14

iglia

0.14

TimeString

0.14

.tencent

0.14

Smarty

0.14

sortable

0.14

Activations Density 0.300%

phrases related to moral and ethical behavior

No Comments

No Known Activations