INDEX

Explanations

references to prominent figures and events in the fashion industry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 quant

-0.17

è¼Ķ

-0.16

estar

-0.15

Ä±rak

-0.15

enville

-0.15

è¾ħ

-0.14

.quant

-0.14

jde

-0.14

wald

-0.14

POSITIVE LOGITS

 Diesel

0.22

Mis

0.20

 Theory

0.20

Theory

0.20

 Tory

0.19

 Reserved

0.19

Dies

0.18

 Given

0.18

 Calvin

0.18

rag

0.18

Activations Density 0.037%

references to prominent figures and events in the fashion industry

No Comments

No Known Activations