INDEX

Explanations

numerical values or references to years and time

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

geber

-0.15

 Distance

-0.15

iÃª

-0.15

imm

-0.15

ADDE

-0.14

ibt

-0.14

Ã³r

-0.14

idebar

-0.14

RefCount

-0.14

POSITIVE LOGITS

til

0.18

ãĥ³ãĤº

0.16

 till

0.16

esty

0.16

icular

0.15

INAL

0.15

Til

0.15

until

0.15

 until

0.14

 Hess

0.14

Activations Density 0.000%

numerical values or references to years and time

No Comments

No Known Activations