INDEX

Explanations

phrases that inquire about or discuss events and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

avra

-0.18

ront

-0.15

vous

-0.14

ÏĦÎ¿Î½

-0.14

cps

-0.14

è©ŀ

-0.14

ÐµÐ·

-0.14

plementation

-0.14

holm

-0.14

ãĥĨãĥ«

-0.14

POSITIVE LOGITS

 happened

0.60

 happen

0.58

 happening

0.52

 happens

0.52

 Happ

0.46

 aconte

0.43

 what

0.40

åıĳçĶŁ

0.40

 happ

0.37

 events

0.36

Activations Density 0.166%

phrases that inquire about or discuss events and their consequences

No Comments

No Known Activations