INDEX

Explanations

references to high-ranking officials and their roles in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ORMAL

-0.15

enz

-0.15

ITU

-0.14

Ping

-0.14

éŀ

-0.14

znÃ¡m

-0.13

atorium

-0.13

pire

-0.13

ÙıÙħ

-0.13

.tem

-0.13

POSITIVE LOGITS

opr

0.15

inta

0.15

otron

0.14

ogl

0.14

uentes

0.14

 Castro

0.14

akra

0.14

/head

0.14

ecta

0.13

ä¼´

0.13

Activations Density 0.071%

references to high-ranking officials and their roles in various contexts

No Comments

No Known Activations