INDEX

Explanations

relationships and interactions between notable individuals

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

inson

-0.17

.Promise

-0.16

errar

-0.15

isphere

-0.15

/watch

-0.14

vana

-0.14

lds

-0.14

âĶģâĶģâĶģâĶģ

-0.14

å¯

-0.14

rollo

-0.14

POSITIVE LOGITS

idual

0.14

 Term

0.13

PageRoute

0.13

 Athena

0.13

 dash

0.13

plementation

0.13

OTOS

0.13

 Gors

0.13

Activations Density 0.442%

relationships and interactions between notable individuals

No Comments

No Known Activations