INDEX

Explanations

codes or identifiers used in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ldb

-0.17

isay

-0.15

ÏĨÎ±

-0.15

readcrumb

-0.14

Ã©m

-0.14

avin

-0.13

rong

-0.13

 BaseService

-0.13

ossip

-0.13

POSITIVE LOGITS

âĢ²

0.17

.com

0.15

.org

0.15

ieber

0.14

 Graham

0.14

consts

0.14

wealth

0.14

 Holmes

0.14

ilig

0.13

Activations Density 0.099%

codes or identifiers used in programming contexts

No Comments

No Known Activations