INDEX

Explanations

words related to sports achievements and rankings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Evening

-0.16

cee

-0.14

æ£Ĵ

-0.14

iona

-0.14

dag

-0.14

orse

-0.14

 puff

-0.14

_refl

-0.14

Wax

-0.14

abin

-0.13

POSITIVE LOGITS

 Tour

0.31

 circuit

0.28

 tour

0.28

Tour

0.27

tour

0.25

 Circuit

0.25

 TOUR

0.25

 circuits

0.23

 tours

0.23

 Tours

0.23

Activations Density 0.053%

words related to sports achievements and rankings

No Comments

No Known Activations