INDEX

Explanations

phrases indicating temporal or chronological relationships

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

MAP

-0.15

loy

-0.14

ourg

-0.14

iod

-0.14

 Produ

-0.13

edition

-0.13

Ð¸Ð¹

-0.13

Loy

-0.13

ikan

-0.13

asta

-0.13

POSITIVE LOGITS

 arrival

0.20

 arrive

0.20

 arrived

0.20

 joining

0.18

 Ð¿ÑĢÐ¸Ð±Ñĭ

0.16

 Powers

0.16

 arriving

0.16

 arriv

0.16

avez

0.15

 lleg

0.15

Activations Density 0.136%

phrases indicating temporal or chronological relationships

No Comments

No Known Activations