INDEX

Explanations

calls for regulatory action or discussions on important issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ensen

-0.15

elter

-0.15

Enlarge

-0.14

elt

-0.14

æµ·éģĵ

-0.14

eldo

-0.14

Serialized

-0.14

 metav

-0.14

è«

-0.14

_featured

-0.13

POSITIVE LOGITS

opor

0.15

rv

0.14

ë²

0.14

æ´

0.14

sville

0.14

.fn

0.14

oller

0.14

 Mont

0.13

dehyde

0.13

ville

0.13

Activations Density 0.522%

calls for regulatory action or discussions on important issues

No Comments

No Known Activations