INDEX

Explanations

references to sports scores and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 niÃªn

-0.15

.Utilities

-0.15

armor

-0.15

onia

-0.14

orse

-0.14

eki

-0.14

eo

-0.14

empl

-0.14

ç§Ģ

-0.13

ãĤĴãģĭ

-0.13

POSITIVE LOGITS

 victory

0.54

 Victory

0.45

win

0.41

 defeat

0.41

 victories

0.40

 wins

0.36

ictory

0.31

 Ð¿Ð¾Ð±ÐµÐ´

0.31

 defeats

0.30

èĥľ

0.29

Activations Density 0.214%

references to sports scores and outcomes

No Comments

No Known Activations