INDEX

Explanations

numerical values related to time or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ICI

-0.15

erah

-0.14

oran

-0.14

nnen

-0.14

ungle

-0.13

 ì¶ľìŀ¥

-0.13

AdapterFactory

-0.13

uble

-0.13

ung

-0.13

emet

-0.13

POSITIVE LOGITS

 Crowley

0.15

£¼

0.14

 nÃ¸

0.14

-ÑĤÐ¾

0.14

.mb

0.14

dj

0.13

oyer

0.13

ëĮĢë¡ľ

0.13

fro

0.13

ersh

0.13

Activations Density 0.081%

numerical values related to time or measurements

No Comments

No Known Activations