INDEX

Explanations

conditional or hypothetical phrasing

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

 McKenzie

-0.19

isset

-0.18

ittest

-0.16

oran

-0.16

ĴĮ

-0.16

ÐµÐºÐ¾Ð¼

-0.15

.WinForms

-0.15

ancock

-0.14

à¹īà¸²à¸¢

-0.14

chn

-0.14

POSITIVE LOGITS

ëł

0.15

idders

0.15

0.14

áº¯p

0.14

aims

0.14

argin

0.14

ÅĽli

0.14

.dataTables

0.14

aveled

0.14

 expect

0.14

Activations Density 0.045%

conditional or hypothetical phrasing

No Comments

No Known Activations