INDEX

Explanations

numeric values or counts related to events or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

oir

-0.16

celed

-0.16

ifold

-0.15

rada

-0.15

wend

-0.15

wahl

-0.14

 Jeho

-0.13

uggy

-0.13

reta

-0.13

ong

-0.13

POSITIVE LOGITS

entials

0.15

aina

0.14

ARP

0.14

angep

0.14

.tp

0.14

(LayoutInflater

0.13

 MULTI

0.13

APT

0.13

apt

0.13

__.

0.13

Activations Density 0.026%

numeric values or counts related to events or quantities

No Comments

No Known Activations