INDEX

Explanations

references to small spaces and their design or organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.16

allee

-0.16

hv

-0.16

_Tis

-0.16

_Lean

-0.16

 PartialView

-0.15

aÃ§

-0.15

cej

-0.15

ghan

-0.14

UMB

-0.14

POSITIVE LOGITS

uren

0.16

issing

0.15

0.14

erek

0.13

 anywhere

0.13

ded

0.13

Rav

0.13

ifu

0.13

--

0.13

Activations Density 0.012%

references to small spaces and their design or organization

No Comments

No Known Activations