INDEX

Explanations

the name "Jean" or variations of it associated with individuals 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 @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.15

udic

-0.15

dÄ±n

-0.15

emd

-0.14

ColumnsMode

-0.14

recht

-0.14

sun

-0.14

ursor

-0.14

.AF

-0.14

xor

-0.13

POSITIVE LOGITS

ette

0.28

ne

0.28

 Bapt

0.21

ie

0.19

ettes

0.18

ene

0.18

ies

0.17

atal

0.17

ett

0.16

etter

0.16

Activations Density 0.007%

the name "Jean" or variations of it associated with individuals in various contexts

No Comments

No Known Activations