INDEX

Explanations

references to the name "Jean"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

abit

-0.18

ombat

-0.17

curity

-0.17

hevik

-0.16

spir

-0.15

udic

-0.15

plevel

-0.15

antium

-0.15

ament

-0.14

ä½Ļ

-0.14

POSITIVE LOGITS

ne

0.40

ette

0.35

ine

0.26

ie

0.26

 Bapt

0.24

ettes

0.23

neau

0.23

 Claude

0.22

etten

0.21

iene

0.21

Activations Density 0.006%

references to the name "Jean"

No Comments

No Known Activations