INDEX

Explanations

technical terms and terminology associated with programming and other specialized subjects

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

hei

-0.16

çļĦåľ°æĸ¹

-0.16

ç´

-0.14

asset

-0.14

 liken

-0.14

kova

-0.14

pit

-0.14

ToStr

-0.14

 Stevens

-0.14

 mens

-0.14

POSITIVE LOGITS

aturas

0.17

Ð¾ÑģÑĤÑĥÐ¿

0.17

atura

0.16

olare

0.16

uptools

0.16

.infinity

0.15

aits

0.14

ton

0.14

.scalablytyped

0.14

 Quar

0.14

Activations Density 0.157%

technical terms and terminology associated with programming and other specialized subjects

No Comments

No Known Activations