INDEX

Explanations

references to miraculous events or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Lightning

-0.15

inium

-0.14

kea

-0.14

mgr

-0.14

way

-0.14

ore

-0.14

iph

-0.14

 Ying

-0.13

light

-0.13

ugh

-0.13

POSITIVE LOGITS

iam

0.22

roring

0.19

rored

0.18

rors

0.18

ACLE

0.18

avit

0.17

iams

0.17

quee

0.17

IAM

0.17

rror

0.17

Activations Density 0.013%

references to miraculous events or experiences

No Comments

No Known Activations