INDEX

Explanations

instances of characters looking or staring at something or someone

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

loud

-0.17

isy

-0.16

 loud

-0.16

.voice

-0.15

earer

-0.15

çļĦå£°éŁ³

-0.15

Äı

-0.14

ibi

-0.14

ecure

-0.14

InBackground

-0.14

POSITIVE LOGITS

 fixed

0.24

 blank

0.22

blank

0.22

 Fixed

0.21

 expect

0.21

 closely

0.20

 FIXED

0.20

fixed

0.20

Fixed

0.19

 transf

0.19

Activations Density 0.167%

instances of characters looking or staring at something or someone

No Comments

No Known Activations