INDEX

Explanations

information related to baby names and their popularity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ñŀ

-0.17

ersh

-0.16

ìļ°

-0.15

odom

-0.14

umont

-0.14

ingham

-0.14

erty

-0.14

ingo

-0.14

brtc

-0.14

erson

-0.14

POSITIVE LOGITS

 baby

0.22

 babies

0.18

 Baby

0.18

akes

0.17

 popularity

0.17

baby

0.17

 variant

0.16

 masculine

0.16

Variant

0.16

.names

0.16

Activations Density 0.004%

information related to baby names and their popularity

No Comments

No Known Activations