INDEX

Explanations

references and citations related to scientific studies or literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ippo

-0.16

kB

-0.16

GOR

-0.15

aris

-0.15

arrants

-0.15

ÑĢÐµÐ¿

-0.15

oulos

-0.14

awning

-0.14

ierz

-0.14

oa

-0.14

POSITIVE LOGITS

 Ross

0.15

iline

0.15

ilet

0.15

dr

0.14

ikut

0.14

ãĥĭãĤ¢

0.14

 abundance

0.14

 Lotto

0.14

agn

0.13

 Feast

0.13

Activations Density 0.029%

references and citations related to scientific studies or literature

No Comments

No Known Activations