INDEX

Explanations

references to data analysis and reporting in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

eniable

-0.15

_VISIBLE

-0.15

TextLabel

-0.15

stat

-0.15

IDO

-0.15

ãģĭãģ®

-0.15

nda

-0.14

 spared

-0.14

inkle

-0.14

Ð½ÐºÐ¸

-0.14

POSITIVE LOGITS

 ÙħØ§Øª

0.16

 Hole

0.16

hole

0.15

taj

0.15

ually

0.15

ì£¼ìĿĺ

0.15

pii

0.14

 hole

0.14

Č↵

0.14

Î³Î¿

0.14

Activations Density 0.917%

references to data analysis and reporting in various contexts

No Comments

No Known Activations