INDEX

Explanations

references to measurements or specifications related to physical properties or products

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ingen

-0.17

 Duis

-0.15

ido

-0.15

_Abstract

-0.15

achen

-0.14

opers

-0.14

ippers

-0.14

pper

-0.14

enville

-0.14

POSITIVE LOGITS

oppel

0.17

atrix

0.16

iliki

0.15

 marginal

0.15

 Coastal

0.14

lix

0.14

ÄŁ

0.14

Byl

0.14

ught

0.14

Alive

0.13

Activations Density 0.673%

references to measurements or specifications related to physical properties or products

No Comments

No Known Activations