INDEX

Explanations

topics related to education and literacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.24

ibold

-0.18

.synthetic

-0.17

ppard

-0.17

ÑĩÑĥÐº

-0.15

CallCheck

-0.15

PRECATED

-0.15

SCALL

-0.15

OTES

-0.15

WithOptions

-0.15

POSITIVE LOGITS

0.17

0.16

 bast

0.16

oron

0.16

fo

0.16

info

0.15

Sch

0.15

Activations Density 0.044%

topics related to education and literacy

No Comments

No Known Activations