INDEX

Explanations

phrases and terminology related to forward-looking statements and their associated risks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Elias

-0.15

ernaut

-0.15

phia

-0.15

mut

-0.14

unya

-0.14

uala

-0.14

 Hlav

-0.14

 Patriot

-0.13

enville

-0.13

kill

-0.13

POSITIVE LOGITS

riz

0.16

edor

0.16

(Collision

0.15

\Migrations

0.15

otal

0.14

åĲĽ

0.14

æĨ

0.13

 defer

0.13

indic

0.13

Ø¹Øª

0.13

Activations Density 0.035%

phrases and terminology related to forward-looking statements and their associated risks

No Comments

No Known Activations