INDEX

Explanations

names and terms associated with religious or spiritual contexts

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

sei

-0.16

 é¡

-0.16

olly

-0.16

ubber

-0.15

Opaque

-0.15

RATE

-0.15

elin

-0.14

angel

-0.14

.accel

-0.14

idget

-0.14

POSITIVE LOGITS

ÑĸÑģ

0.15

ovel

0.15

ime

0.14

Ð¾ÑĤÐ¸

0.14

MOTE

0.14

.FLAG

0.13

.override

0.13

 bail

0.13

ues

0.13

 mand

0.13

Activations Density 0.018%

names and terms associated with religious or spiritual contexts

No Comments

No Known Activations