INDEX

Explanations

hypothetical scenarios and questions about change and possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

strup

-0.16

???

-0.15

umbing

-0.15

 whereas

-0.14

FE

-0.14

fur

-0.14

umably

-0.13

imuth

-0.13

tera

-0.13

QUIRES

-0.13

POSITIVE LOGITS

airy

0.15

 Skeleton

0.15

PCP

0.15

acd

0.15

 would

0.14

à¸¸à¸Ľ

0.14

 Would

0.14

cy

0.14

astes

0.14

Kaf

0.14

Activations Density 0.078%

hypothetical scenarios and questions about change and possibilities

No Comments

No Known Activations