INDEX

Explanations

references to specific organizations or teams, particularly those related to names or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ihan

-0.17

uling

-0.17

ares

-0.17

elli

-0.16

illon

-0.16

aux

-0.16

-0.15

ÑĥÐµÑĤ

-0.15

UX

-0.15

Ã©es

-0.15

POSITIVE LOGITS

ideos

0.15

czy

0.15

iks

0.15

inka

0.15

rios

0.14

'gc

0.14

arness

0.14

ik

0.14

.addComponent

0.14

ika

0.14

Activations Density 0.147%

references to specific organizations or teams, particularly those related to names or institutions

No Comments

No Known Activations