INDEX

Explanations

proper nouns related to names, organizations, and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

anova

-0.17

lon

-0.15

itian

-0.15

ynes

-0.14

oner

-0.14

ion

-0.14

è²»

-0.14

 adel

-0.14

è´¹

-0.14

POSITIVE LOGITS

ervas

0.16

ÅĻeb

0.15

ãĥĭãĤ¢

0.15

 ÐĿÑĸ

0.14

iÅ¾

0.14

appoint

0.14

__$

0.13

_arch

0.13

ÎķÎł

0.13

 nonatomic

0.13

Activations Density 0.020%

proper nouns related to names, organizations, and numerical data

No Comments

No Known Activations