INDEX

Explanations

references to the word "esp," likely indicating a focus on communication of special interests or alerts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

veau

-0.18

campo

-0.16

 exponent

-0.15

oref

-0.15

erable

-0.15

ushima

-0.14

aires

-0.14

Ã§as

-0.14

ATUS

-0.14

Locale

-0.14

POSITIVE LOGITS

RefCount

0.15

arda

0.14

oS

0.14

pedia

0.14

uju

0.14

 Appeal

0.13

.ContentType

0.13

 holog

0.13

leh

0.13

leton

0.13

Activations Density 0.005%

references to the word "esp," likely indicating a focus on communication of special interests or alerts

No Comments

No Known Activations