INDEX

Explanations

instances of the term "OK" and its variations in context

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

coni

-0.18

Å¯l

-0.17

anca

-0.17

osate

-0.16

ascar

-0.16

ichel

-0.15

eldon

-0.15

ongodb

-0.15

ADOR

-0.15

OLT

-0.14

POSITIVE LOGITS

tober

0.34

lahoma

0.29

ahoma

0.22

anagan

0.19

amoto

0.18

AY

0.17

lah

0.17

 Computer

0.16

Ok

0.15

hots

0.15

Activations Density 0.028%

instances of the term "OK" and its variations in context

No Comments

No Known Activations