INDEX

Explanations

instances of the word "Go" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ÙĨØ¯Ùĩ

-0.15

è·¡

-0.15

piler

-0.15

uously

-0.15

bout

-0.15

udit

-0.14

TK

-0.14

elay

-0.14

umin

-0.14

unto

-0.14

POSITIVE LOGITS

Go

0.25

Go

0.23

-go

0.22

Ã»t

0.21

ody

0.21

tha

0.19

ings

0.19

 figure

0.19

thic

0.18

osed

0.18

Activations Density 0.022%

instances of the word "Go" and its variations

No Comments

No Known Activations