INDEX

Explanations

phrases related to events, notable occurrences, or specific themes in articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

warts

-0.14

zM

-0.14

asin

-0.14

zo

-0.14

idon

-0.14

aska

-0.14

Verse

-0.14

appa

-0.13

ordon

-0.13

POSITIVE LOGITS

 Dalton

0.17

à¥°

0.15

Æ°

0.15

istrar

0.14

ocket

0.14

ãĥ

0.14

 Insecta

0.14

æĮĻ

0.13

ó

0.13

_usec

0.13

Activations Density 0.046%

phrases related to events, notable occurrences, or specific themes in articles

No Comments

No Known Activations