INDEX

Explanations

web links and references to online content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.18

ovol

-0.15

 Claw

-0.15

prot

-0.15

eg

-0.15

alle

-0.14

estion

-0.14

olia

-0.14

erd

-0.14

POSITIVE LOGITS

urma

0.15

aines

0.15

ÚĨÙĩ

0.15

 Redistributions

0.14

aggable

0.14

immer

0.14

nyder

0.14

adium

0.14

ogan

0.14

 NVIC

0.14

Activations Density 0.035%

web links and references to online content

No Comments

No Known Activations