INDEX

Explanations

references to IQ and intelligence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

.scalablytyped

-0.18

rij

-0.15

ISCO

-0.15

-desc

-0.14

FLT

-0.14

 federal

-0.14

 hatÄ±r

-0.14

Breadcrumb

-0.13

Ð¸Ð½Ð¾Ðº

-0.13

NEG

-0.13

POSITIVE LOGITS

 overhead

0.17

rap

0.15

 Hood

0.15

oni

0.15

thr

0.14

 Ð·Ð°Ð³

0.14

RelativeTo

0.14

iazza

0.14

 destiny

0.14

ÑĤÐ°Ð»

0.14

Activations Density 0.007%

references to IQ and intelligence

No Comments

No Known Activations