INDEX

Explanations

the name "Jon" and its variations in various contexts

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

pond

-0.20

dens

-0.19

ucken

-0.17

itious

-0.16

.scalablytyped

-0.16

agos

-0.15

ÙĪÛĮÙĨØª

-0.15

zim

-0.14

zm

-0.14

(strtolower

-0.14

POSITIVE LOGITS

athon

0.26

ny

0.24

nie

0.20

ned

0.19

ning

0.18

athan

0.18

oth

0.17

ctions

0.17

atural

0.17

atham

0.16

Activations Density 0.009%

the name "Jon" and its variations in various contexts

No Comments

No Known Activations