INDEX

Explanations

references to specific locations and notable figures within a sports context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 mountain

-0.15

hod

-0.15

Ø³ÙĦØ§Ùħ

-0.14

itar

-0.14

iges

-0.14

elong

-0.14

vang

-0.14

AMPL

-0.13

 Mountain

-0.13

POSITIVE LOGITS

 Houston

0.48

Houston

0.44

ouston

0.38

 Astros

0.34

 Texans

0.28

0.26

 Rice

0.26

 Harris

0.24

 Katy

0.23

Activations Density 0.064%

references to specific locations and notable figures within a sports context

No Comments

No Known Activations