INDEX

Explanations

mentions of on-site locations or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 Publishers

-0.16

adh

-0.15

CellValue

-0.15

Pic

-0.15

ãģ¨ãģĦ

-0.14

arp

-0.14

ãĥ¼ãĥķ

-0.14

icher

-0.14

hire

-0.14

 kurs

-0.13

POSITIVE LOGITS

TRS

0.16

Î¹ÎºÎ¿

0.16

isphere

0.15

orsche

0.15

orida

0.14

 CONSEQUENTIAL

0.14

mouseleave

0.14

slu

0.14

ripe

0.14

EDA

0.14

Activations Density 0.009%

mentions of on-site locations or services

No Comments

No Known Activations