INDEX

Explanations

instances of the word "at" and variations of the term "sport."

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

olo

-0.16

 Barcl

-0.15

borough

-0.15

 Florence

-0.15

 cust

-0.15

Flo

-0.15

cheid

-0.14

aret

-0.14

IP

-0.14

Flo

-0.14

POSITIVE LOGITS

haf

0.18

IZ

0.17

enville

0.16

igma

0.15

heits

0.15

ebo

0.15

iec

0.15

czy

0.15

:UITableView

0.15

kop

0.15

Activations Density 0.002%

instances of the word "at" and variations of the term "sport."

No Comments

No Known Activations