INDEX

Explanations

names and professional affiliations related to sports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Meaning

-0.15

 Bruins

-0.15

ata

-0.15

mlink

-0.14

ught

-0.14

circ

-0.13

ATA

-0.13

aton

-0.13

 Braun

-0.13

cia

-0.13

POSITIVE LOGITS

erek

0.17

uzzi

0.17

kit

0.15

IRMWARE

0.14

loo

0.14

Kit

0.14

lineno

0.14

-kit

0.14

anna

0.14

.createClass

0.14

Activations Density 0.090%

names and professional affiliations related to sports

No Comments

No Known Activations