INDEX

Explanations

comparisons and assessments of sequels in video game reviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 coincidence

-0.15

ertoire

-0.15

afil

-0.14

 Ferd

-0.14

ola

-0.14

udit

-0.14

endon

-0.14

 ../../../

-0.13

rai

-0.13

ayer

-0.13

POSITIVE LOGITS

 sequel

0.55

 sequ

0.49

sequ

0.46

 Sequ

0.44

 follow

0.36

ç»Ń

0.36

 continuation

0.34

çºĮ

0.31

follow

0.31

seq

0.30

Activations Density 0.139%

comparisons and assessments of sequels in video game reviews

No Comments

No Known Activations