INDEX

Explanations

references to divine commandments and moral warnings

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

.scalablytyped

-0.15

_encoded

-0.15

yna

-0.14

licer

-0.14

 Äĳá»Ļng

-0.14

orus

-0.14

åĬ¨

-0.14

bero

-0.14

orris

-0.13

_css

-0.13

POSITIVE LOGITS

cus

0.15

0.14

LECT

0.14

 feed

0.14

riba

0.13

URE

0.13

lew

0.13

 Feed

0.13

_Handle

0.13

à¥įà¤Łà¤°

0.13

Activations Density 0.342%

references to divine commandments and moral warnings

No Comments

No Known Activations